Federated Noisy Labels Learning (FNLL) allows global model to be jointly trained on multiple clients with varying degrees of noisy labels while preserving privacy, and despite recent research advances, distinguishing between client clean and noisy samples is still tricky since the distribution of labels among clients is always both noisy and class-imbalanced, leading to the poor performance of existing FNLL methods. To address this problem, we propose a novel framework called FedPN, the first framework to utilize Contrastive Language-Image Pre-training (CLIP) for federated noisy labels tasks. Then, to achieve higher performance for the global model, we introduce an attention based Prototype Adapter to identify more plausible local data for local model training, further improving training stability. We validate the effectiveness of FedPN by conducting extensive experiments on benchmark datasets under both Independently and Identically Distributed (IID) and Non-IID data partitions. The experimental results show that FedPN can effectively filter noisy samples from different clients, and compared with the state of-the-art FNLL method, the FedPN achieves at most and at least 8.39% and 0.88% performance improvement in the case of highly heterogeneous noisy labels.

The rapid growth of Internet of Things (IoT) devices has heightened hardware security concerns, particularly with the emergence of hardware Trojans (HTs) as malicious components in integrated circuits. These HTs pose significant threats to information privacy and system performance. The early detection methods rely on golden references and domain knowledge, limiting their implementation in large-scale integrated circuits. Traditional machine learning-based HT detections can effectively identify infected circuits without golden chips. However, locating and evaluating the specific behavior of HTs in vast and complex circuits is challenging. To address these challenges, this paper presents an HT Object Detection (HTOD) problem, which involves two primary tasks: identifying the boundaries and sizes of HTs within circuits and distinguishing between different HT behaviors. We have developed a two-stage HT object detection framework based on a bidirectional jumping knowledge network called HTOD-BGNN to solve the HTOD problem, which enables progressive refinement of localized regions. It incorporates enhanced base-type features to ensure scalability and information retention during modeling. Additionally, the implementation of sample augmentation alleviates the challenges of sample imbalance and scarcity. The proposed method enables more intelligent circuit detection, achieving 100% and 87.5% detection rates for Trojan triggering and payload behaviors, respectively. It demonstrates superior localization performance and effective generalization to unseen circuit scenarios via its region refinement mechanism, achieving F1-scores of 54.01% on TrustHub and 90.04% on TRIT datasets.

Buy Now Pay Later (BNPL) is a rapidly proliferating e-commerce model, offering consumers to get the product immediately and defer payments. Meanwhile, emerging blockchain technologies endow BNPL platforms with digital currency transactions, allowing BNPL platforms to integrate with digital wallets. However, the transparency of transactions causes critical privacy concerns because malicious participants may derive consumers' financial statuses from on-chain asynchronous payments. Furthermore, the newly created transactions for deferred payments introduce additional time overhead, which weakens the scalability of BNPL services. To address these issues, we propose an efficient and privacy-preserving blockchain-based asynchronous payment scheme (Epass), which has promising scalability while protecting the privacy of on-chain consumer transactions. Specifically, Epass leverages locally verifiable signatures to guarantee the privacy of consumer transactions against malicious acts. Then, a privacy-preserving asynchronous payment protocol is further constructed by leveraging time-release encryption to control trapdoors of the redactable blockchain, reducing time overhead by modifying transactions for deferred payment. We give formal definitions and security models, generic structures, and formal proofs for Epass. Extensive comparisons and experimental analysis show that Epass achieves KB-level communication costs, and reduces time overhead by more than four times in comparisons with locally verifiable signatures and Go-Ethereum private test networks.

Federated learning (FL) enables multiple clients to collaboratively train machine learning (ML) models without exposing their private data. The recent surge in poisoning attacks and privacy leakage against FL has driven the development of secure federated learning (SFL) solutions. However, existing SFL schemes show inadequate performance when confronted with non-independent and identically distributed ( non-IID) data. In addition, traditional SFL architectures are prone to single point of failure (SPOF) issues due to the heavy computational and communication burdens imposed on a single server. In response to these issues, a novel blockchain-based secure federated learning (BSFL) framework is proposed in this paper. Specifically, we devise a proof of verification (PoV) consensus protocol to identify poisoning attacks under non-IID situations, while preventing the waste of computational and communication resources. Subsequently, we present a personalized differential privacy (PDP) mechanism, which achieves comprehensive privacy protection with lower noise levels. Furthermore, the integration of the blockchain with the proposed reward mechanism overcomes SPOF and fosters constructive participation through transparent processes. Formal theoretical analysis demonstrates the security, privacy, and efficiency of our framework. Extensive experimental evaluations indicate that BSFL exhibits strong resilience against various poisoning attacks and achieves better model accuracy compared to existing SFL solutions.

In edge computing environments, app vendors improve user access by caching data across geographically distributed edge servers. However, this architecture remains vulnerable to intentional attacks and accidental failures. Thus, distributed data must be jointly inspected, corruption identified, and repaired efficiently. Addressing these challenges requires a method that efficiently manages vendor resources and minimizes cost. To meet these needs, we propose${\text{O}^{2}\text{DI}}$, an innovative tag-based verifiable outsourcing mechanism with the following capabilities: (i) it enables app vendors to verify cached data on edge servers without accessing the original data, significantly reducing I/O and storage overhead; (ii) it introduces a cutting-edge online/offline technique that improves computational efficiency for both edge servers and app vendors; (iii) it implements a novel batch verification process, enabling rapid and simultaneous verification of multiple files across edge servers; and (iv) it ensures efficient localization and repair of corrupted data. Our comprehensive analysis of${\text{O}^{2}\text{DI}}$demonstrates its robust security within the random oracle model, along with significant improvements in speed and cost-effectiveness over existing methods. Moreover, to demonstrate the practical use of${\text{O}^{2}\text{DI}}$in a real-world system, we present a testbed experiment implemented as a publicly accessible web application that effectively showcases the capabilities of${\text{O}^{2}\text{DI}}$.

Backdoor attacks and adversarial attacks are two major security threats to deep neural networks (DNNs), with the former one is a training-time data poisoning attack that aims to implant backdoor triggers into models by injecting trigger patterns into training samples, and the latter one is a testing-time attack trying to generate adversarial examples (AEs) from benign images to mislead a well-trained model. While previous works generally treat these two attacks separately, the inherent connection between these two attacks is rarely explored. In this paper, we focus on bridging backdoor and adversarial attacks and observe two intriguing phenomena when applying adversarial attacks on an infected model implanted with backdoors: 1) the sample is harder to be turned into an AE when the trigger is presented; 2) the AEs generated from backdoor samples are highly likely to be predicted as its true labels. Inspired by these observations, we proposed a novel backdoor defense method, dubbed Adversarial-Inspired Backdoor Defense (AIBD), to isolate the backdoor samples by leveraging a progressive top-q scheme and break the correlation between backdoor samples and their target labels using adversarial labels. Through extensive experiments on various datasets against six state-of-the-art backdoor attacks, the AIBD-trained models on poisoned data demonstrate superior performance over the existing defense methods.

Graph Neural Networks (GNNs) have exhibited remarkable capabilities for dealing with graph-structured data. However, recent studies have revealed their fragility to adversarial attacks, where imperceptible perturbations to the graph structure can easily mislead predictions. To enhance adversarial robustness, some methods attempt to learn robust representation through improving GNN architectures. Subsequently, another approach suggests that these GNNs might taint feature information and have poor classifier performance, leading to the introduction of Graph Contrastive Learning (GCL) methods to build a refining-classifying pipeline. However, existing methods focus on global-local contrastive strategies, which fails to address the robustness issues inherent in the contexts of adversarial robustness. To address these challenges, we propose a novel paradigm named GRANCE to enhance the robustness of learned representations by shifting the focus to local neighborhoods. Specifically, a dual neighborhood contrastive learning strategy is designed to extract local topological and semantic information. Paired with a neighbor estimator, the strategy can learn robust representations that are resilient to adversarial edges. Additionally, we also provide an improved GNN as classifier. Theoretical analyses provide a stricter lower bound of mutual information, ensuring the convergence of GRANCE. Extensive experiments validate the effectiveness of GRANCE compared to state-of-the-art baselines against various adversarial attacks.

Decoding gene regulatory networks is critical for understanding cell identity and disease. While single-cell multiomics technologies can measure both gene expression and chromatin accessibility, precisely linking regulatory elements to their target genes remains a great challenge. To this end, we propose MICA, a deep learning interpretable model that treats gene regulation as a bi-directional transition from “regulatory syntax” to “functional language”. The core of MICA is a bilinear attention mechanism that performs end-to-end optimization through a cross-modal bidirectional generative task. The task forces the model to learn attentional weights with predictive power to go beyond simple correlations and capture functional regulatory dependencies. Experimental results show that our approach exhibits outstanding performance in the cross-modal generation task, and in a subsequent interpretability validation we corroborate from multiple perspectives that the resulting attentional mechanism is biologically meaningful. This work provides a powerful and interpretable computational tool for deciphering complex gene regulatory codes at single-cell resolution, offering new perspectives for systematic understanding of cellular heterogeneity.

In recent years, privacy concerns have been receiving increasing attention. Federated learning (FL) has emerged to address privacy challenges in machine learning. In this framework, a group of clients collaborates with a server, where clients upload model parameters instead of raw data. In FL, a key challenge is the presence of non-independent and identically distributed data among clients. To address this issue, we propose a personalized federated learning algorithm (FedMKD) that fully considers the characteristics of the previous round's model. Our algorithm leverages knowledge distillation and gradient descent to optimize the proportion of global model parameters used during the initialization process. FedMKD combines the strengths of the global and memory models to initialize the local model. It effectively retains historical information during training, enhancing the local model's performance. Extensive experimental results demonstrate the effectiveness of our proposed algorithm in addressing statistical heterogeneity issues. FedMKD achieves up to a 10.66% improvement in test accuracy compared to eight state-of-the-art baselines.

In machine learning (ML), data deletion involves more than just removing data from a dataset. Machine unlearning enables ML models to eliminate the effects of specific data that needs to be deleted. Under zero-glance settings, we may lack the right to utilize the data slated for removal during unlearning, thereby heightening the complexity. To address this challenge, we propose UISPS, which employs data-free inversion to generate replacement data for unavailable forgotten data. Utilizing the generated data, we propose selective parameter suppression to address the issue of catastrophic forgetting during unlearning effectively. Its interpretability improves the reliability of unlearning under zero-glance conditions. The experiments demonstrate that UISPS performs forgotten tasks with commendable results. Meanwhile, UISPS maintains higher accuracy on retained data, improving it by up to 3.34% while reducing the attack success rate of membership inference attacks by 25.85% ∼ 39.54% compared to the state-of-the-art.

Facing the growing diversity of multi-view data, multi-view graph-based models have made encouraging progress in handling multi-view data modeled as graphs. Graph Contrastive Learning (GCL) naturally fits multi-view graph data by treating their inherent views as augmentations. However, the development of GCL on multi-view graph data is still in the infant stage. Challenges remain in designing strategies that coordinate preprocessing and contrastive learning, and in developing model architectures that automatically meet the needs of diverse views. To tackle these, we propose a framework named CAMEL, which refines consistency learning by introducing a tailored contrastive paradigm for multi-view graphs. Initially, we theoretically analyze the positive effect of edge-dropping preprocessing on the consistency and quantify the factors that influence it. Paired with a learnable model architecture, the proposed adaptive edge-dropping preprocessing strategy is guided by dynamic topology, making the heterogeneity of views more controllable and better aligned with contrastive learning. Finally, we design a neighborhood consistency multi-view contrastive objective that enhances consistency information interaction by extending positive samples. Extensive experiments on downstream tasks, including node classification and clustering, validate the superiority of our proposed model.

Federated learning remains vulnerable to backdoor attacks through malicious parameter updates, with existing defenses limited by homogeneous data assumptions or reliance on gradient anomaly detection. We reveal that FedAvg's critical flaw lies in malicious feature extractor propagation: aggregating poisoned extractors degrades defense accuracy to <70% across five benchmarks, while benign extractors with poisoned headers retain an average of 89.36% defense accuracy. Therefore, we propose FeatShield, a feature-space isolation framework that prevents backdoor propagation via non-aggregated local extractors trained on clean client data. FeatShield introduces 1) variance-aware alignment, adaptively balancing client-specific features and global consistency using local variance metrics, and 2) adversarial feature synthesis, generating non-linear synthetic features via GAN to enhance the global prediction header's generalization on main tasks. Extensive experiments on eight real-world datasets show that FeatShield achieves the best defense performance. For instance, under heterogeneous data (Dirichlet β=0.5) and strong attacks (50% malicious clients), FeatShield achieves 99.26-99.89% defense accuracy and main task accuracy exceeding FedAvg by 1.32-5.70%, demonstrating its superior resistance to backdoor attacks without sacrificing the benign performance.

With the growing significance of federated learning (FL) in preserving data privacy, addressing the challenge of noisy labels has become critical. Conventional methods typically focus on filtering or reweighting noisy samples, often overlooking their inherent informational value. To exploit this value, we propose FedUNL, a novel framework for robust FL under label noise. FedUNL uses a Gaussian Mixture Model (GMM) to identify noisy clients and samples based on sample and class losses. Noisy models are then constructed with these samples, and knowledge distillation is employed to extract useful knowledge, supporting main model training and enabling effective noise correction. Distinct strategies are applied to train clean and noisy clients. Experimental results demonstrate that FedUNL improves accuracy by 0.31% to 3.41% over state-of-the-art (SOTA) methods, particularly excelling in challenging scenarios with high noise levels and non-IID data distributions.

In black-box attack scenarios, enhancing the transferability of adversarial samples for targeted attacks presents significant challenges and is crucial for real-world applications. Most current research focuses on attack strategies that rely on data augmentation or generator training, which tend to perform well in untargeted attacks but exhibit limited effectiveness in targeted attack scenarios. To address this, we propose a novel framework for adversarial sample generation called TADA, designed to modify the sample distribution and improve transferability in both attack scenarios. TADA consists of two key components. First, we change the image distribution in the diffusion model by using the gradient of deviation between images to guide the denoising process. Second, we introduce a fine-tuning strategy that uses the gradient norm of the label loss as a constraint to bootstrap the loss to a flat minimum and regularize the penalty for large weight values. With these two strategies, TADA can more effectively modify the original distribution of images to generate highly transferable adversarial examples. Through extensive experiments with various general-purpose training and defense models, our TADA consistently outperform state-of-the-art attack methods in both scenarios. Notably, the reconstructed images enhance the transferability of existing attack methods. For example, the CFM attack achieves a 12.3% increase in success rate for targeted attacks when transitioning from Res-50 to Inc-Res-v2.

The integration of edge computing in the Internet of Medical Things (IoMT) offers great potential for decentralized healthcare services but introduces challenges due to the limited computational capabilities of IoMT devices. Ensuring data security and performance is critical, especially when sensitive medical data pass through untrusted edge devices. Traditional cryptographic methods, such as encryption and signing, are impractical for resource-constrained sensors, particularly when securing data for multiple recipients in an anonymous manner. In this paper, we propose an efficient online/offline broadcast remote signcryption scheme to address these challenges. Our scheme enables medical sensors to securely signcrypt data for multiple recipients, ensuring both confidentiality and integrity. It further guarantees that the ciphertext does not disclose the identities of the recipients, thereby preserving their anonymity. It minimizes online computation by offloading resource-intensive tasks to offline processes. This approach enables remote verification without accessing the original data. Implemented within an edge computing framework, the scheme reduces delays in accessing user data while maintaining robust security guarantees. The security of our solution is rigorously proven under the Bilinear Diffie-Hellman assumption, and real-world implementation demonstrates that the scheme is highly efficient, making it well-suited for practical IoMT applications in healthcare.

In communication systems, ensuring both data integrity and confidentiality is crucial. Traditional methods, such as encryption and signature schemes, handle these aspects separately, leading to inefficiencies. Signcryption techniques, which address both requirements simultaneously, present a more efficient alternative. Nonetheless, they are unsuitable for cloud storage systems due to their reliance on original files for data auditing. Remote data integrity checking (RDIC) methods resolve this issue but compromise data confidentiality. To bridge the gap between signcryption and RDIC approaches, remote signcryption (RSC) has been proposed. However, existing RSC methods lack support for public auditing, rendering data auditing non-outsourcable. This paper introduces publicly verifiable remote signcryption (PVRSC) to address this shortcoming and presents the first concrete PVRSC scheme with public verifiability. We define the security model for PVRSC and prove its robustness based on the hardness of the Bilinear Diffie-Hellman (BDH) problem. Our implementation on real data shows that PVRSC significantly outperforms existing methods, achieving speeds up to 100 times faster and reducing communication costs by half compared to RDIC methods. For outsourced data up to 5MB, PVRSC maintains a communication cost below 8KB during data recovery, a substantial improvement over classical signcryption approaches, which exceed 5MB.

With the rapid growth of encrypted image data outsourced to cloud servers, achieving data confidentiality and searchability in cloud-assisted Internet of Things (IoT) environments has become increasingly feasible. However, achieving high efficiency and strong security simultaneously over large-scale encrypted image datasets remains a challenge. To address this, we propose a novel efficient and secure content-based image retrieval scheme in cloud-assisted IoT. Specifically, our scheme leverages lattice-based fully homomorphic encryption and homomorphic comparison techniques, utilizing Cheon-Kim–Kim-Song’s batch processing and single-instruction-multiple-data capabilities. This approach significantly reduces the overhead of fully homomorphic computations, making the query process computational complexity independent of dataset size under certain conditions. Moreover, by integrating private information retrieval technology, the scheme enhances privacy by hiding access patterns of image data. Formal security analysis demonstrates that our scheme achieves indistinguishability against chosen-plaintext attack (IND-CPA), and extensive experiments based on real datasets confirm that our scheme is both practical and efficient for real-world applications.

Ensuring the security of data outsourced to cloud is a prerequisite for the application of Internet of Things (IoT) in actual production. Secure search based on homomorphic encryption can provide high security and require no expensive setup procedure, which can be applied to resource-limited devices in IoT. However, the existing schemes usually have poor search performance and do not consider multiowner setting. To solve these issues, we propose an efficient homomorphic encryption-based secure search scheme in multiowner setting. Specifically, we construct a secure search protocol based on multikey homomorphic encryption, which can be deployed in multiowner setting. Meanwhile, we improve the efficiency of our scheme by optimizing the search algorithm. Formal security analysis proves that our scheme is secure against chosen plaintext attack, and extensive experiments demonstrate that our scheme improves the search efficiency by$1000\times $when compared with state-of-the-art solutions.

The smart grid, which integrates with many advanced technologies and applications, brings great convenience for the data interaction between users and service providers. It is inevitable to collect a large amount of fine-grained, real-time data of users. However, these data transmissions have a huge communication burden and security issue in the smart grid. Therefore, this paper proposes an Edge Computing and Blockchain-based Security Data Aggregation scheme (ECBSecDA) for secure and fast data aggregation. This scheme is a three-layer data aggregation framework including user layer, edge computing layer and blockchain layer, and each layer uses Paillier cryptosystem to encrypt and then aggregate data. In user layer, we improve group signature by sharing group parameters for reducing communication overhead. In edge computing layer, we use group signature tracking algorithm to identify the attackers’ identity and make them re-register. Then, we design an edge node diversion algorithm to deal with big data flow issues for the aggregated data from the user layer, achieving low latency communication. Finally, the blockchain layer further aggregates and manages the received data from edge computing layer. This paper analyzes the security of our scheme, which ensures the privacy of users’ data. We conducted some comparisons with relevant work, and experimental results show that our scheme has lower computation cost and communication overhead.

In the realm of secure data outsourcing, verifiable dynamic searchable symmetric encryption (VDSSE) enables a client to verify search results obtained from an untrusted server while protecting the data privacy. Nevertheless, the storage cost of verification structure in some schemes escalates linearly with the number of keywords, and the generation of proofs demands a substantial number of exponentiation operations. Moreover, some schemes overlook forward and backward security in the dynamic database. In this article, we introduce FB-VDSSE, an advanced VDSSE scheme that ensures both forward and backward security. Specifically, we introduce an efficient accumulation commitment verification structure (AC-VS) that attains a commitment verification value with a constant-size storage cost. Based on the AC-VS, we further propose a forward and backward secure VDSSE scheme. Within this scheme, the server exclusively generates a membership proof at the corresponding index of the vector, reducing the computation cost associated with the search operation. Finally, we provide the security proof and functional comparison, demonstrating that our scheme effectively ensures forward security, backward security, and verifiability. Additionally, the experimental evaluations underscore the efficiency of our scheme, showcasing its superior performance compared to relevant schemes in practical scenarios.

Due to the complexity of integrated circuit design and manufacturing process, an increasing number of third parties are outsourcing their untrusted Intellectual Property (IP) cores to pursue greater economic benefits, which may embed numerous security issues. The covert nature of hardware Trojans (HTs) poses a significant threat to cyberspace, and they may lead to catastrophic consequences for the national economy and personal privacy. To deal with HTs well, it is not enough to just detect whether they are included, like the existing studies. Same as malware, identifying the attack intentions of HTs, that is, analyzing the functions they implement, is of great scientific significance for the prevention and control of HTs. Based on the fined detection, for the first time, this paper proposes a two-stage Graph Neural Network model for HTs’ multifunctional classification, GNN4HT. In the first stage, GNN4HT localizes HTs, achieving a notable True Positive Rate (TPR) of 94.28 the Trust-Hub dataset and maintaining high performance on the TRTC-IC dataset. GNN4HT further transforms the localization results into HT Information Graphs (HTIGs), representing the functional interaction graphs of HTs. In the second stage, the dataset is augmented through logical equivalence for training and HT functionalities are classified based on the extracted HTIG from the first stage. For the multifunctional classification of HTs, the correct classification rate reached as high as 80.95% at gate-level and 62.96% at RTL. This paper marks a breakthrough in HT detection, and it is the first to address the multifunctional classification issue, holding significant practical importance and application prospects.

Image manipulation has sparked widespread concern due to its potential security threats on the Internet. The boundary between the authentic and manipulated region exhibits artifacts in image manipulation localization (IML). These artifacts are more pronounced in heterogeneous image splicing and homogeneous image copy-move manipulation, while they are more subtle in removal and inpainting manipulated images. However, existing methods for image manipulation detection tend to capture boundary artifacts via explicit edge features and have limitations in effectively addressing subtle artifacts. Besides, feature redundancy caused by the powerful feature extraction capability of large models may prevent accurate identification of manipulated artifacts, exhibiting a high false-positive rate. To solve these problems, we propose a novel edge-aware network (EAN) to capture boundary artifacts effectively. This network treats the image manipulation localization problem as a segmentation problem inside and outside the boundary. In EAN, we develop an edge-aware mechanism to refine implicit and explicit edge features by the interaction of adjacent features. This approach directs the encoder to prioritize the desired edge information. Also, we design a multi-feature fusion strategy combined with an improved attention mechanism to enhance key feature representation significantly for mitigating the effects of feature redundancy. We perform thorough experiments on diverse datasets, and the outcomes confirm the efficacy of the suggested approach, surpassing leading manipulation localization techniques in the majority of scenarios.

Recruiting users in mobile crowdsensing (MCS) can make the platform obtain high-quality data to provide better services. Although the privacy leakage during the process of user recruitment has received a lot of research attention, none of the existing work considers the evaluation of the sensing quality of privacy-preserving data submitted by users, which makes the platform incapable of recruiting users suitably to obtain high-quality sensing data, thereby reducing the reliability of MCS services. To solve this problem, we first propose a sensing quality evaluation method based on the deviation and variance of sensing data. According to it, the platform can obtain the sensing quality of privacy-preserving data for each user during the recruitment. Then we model the user recruitment with a limited budget platform as aCombinatorial Multi-Armed Bandit (CMAB)game to determine the recruited users based on the sensing quality of data obtained by evaluation. Finally, we theoretically prove that our algorithm satisfies differential privacy and the upper bound on theregretof rewards is restricted. Experimental results show that our proposal is superior in various properties, and our method has a 73.67% advantage in accumulated sensing qualities compared with comparison schemes.

The landscape of cyberattacks has transcended from mere hobbyist pursuits of cybercriminals to a lucrative business model, facilitating their sustenance. Concurrently, the cybercrime market has evolved into a complex ecosystem. Empowered by this environment, cybercriminal tactics have evolved from simple, isolated activities to intricate and coordinated cyberattacks. In this article, we reveal a new type of cyberattack paradigm termed Attack Exploiting Cyber-arms Industry (AECI), which, despite its potential for severe impact, requires less investment and entails fewer obstacles and risks compared to traditional methods. However, this type of attack is still neglected by security researchers and communities and this is the first work focusing on this type of attack. To elucidate AECI, we provide an overview of the cyber-arms industry and introduces an attack model. The model dissects each phase of AECI to illuminate its operational mechanics and strategic imperatives. Furthermore, to assess its potential impact, a mathematical model is proposed to estimate the scale of infection attributable to AECI. Through analysis of a specific attack case, our findings demonstrate that AECI can generate significant impacts within a brief timeframe, akin to the magnitude observed with the Mirai botnet. The proposed model is demonstrated to prove instrumental in effectively analyzing AECI and providing accurate estimations of its infection scale.

While multi-key homomorphic encryption (MKHE) ensures privacy in federated learning (FL) by encrypting model updates, its requirement for aggregate ciphertext decryption and dropout handling increases communication rounds during aggregation. To enable secure multi-key aggregation with low communication rounds, we propose SAMK. SAMK enables the server to compute the sum of model updates from clients participating in FL, while keeping these updates encrypted by different keys throughout the computation. By utilizing the polynomial property of the BFV ciphertext, SAMK successfully implements individual decryption of the aggregated ciphertext (encrypted under multiple keys) by each client using their respective keys, resulting in low communication rounds. It means that in SAMK, all client interactions are avoided and the client-server interaction is only once (ciphertext uploads and downloads) in each round of aggregation computation. In addition, SAMK is robust to any number of clients dropping out at any time, and the client who has dropped out after uploading model updates, can still get the correct aggregation result upon reconnecting. We prove the security of SAMK for semi-honest server and clients, where client collusion is also considered. At last, we implement SAMK and comprehensively evaluate its performance to demonstrate its practicability.

Next Point-of-Interest (POI) recommendation plays an important role in various Location-Based Social Networks (LBSNs). It main objective is to predict the user's next interested POI based on previous check-in information. Most existing research treats next POI recommendation as a sequence prediction problem, ignoring collaborative signals from other users as well as security. Instead, a Differential Privacy-based Transformer Framework for Next POI Recommendation (LDPTRec) is proposed, which focuses on dynamic privacy protection, category-specific temporal modeling, and privacy-preserving sequence integration. (1) A privacy trajectory flow graph is constructed by using social-aware edge local differential privacy to protect users behavioral and location privacy. (2) A novel temporal category-aware context embedding algorithm is designed to capture diverse temporal patterns of POI categories. (3) A DP-Transformer algorithm with theoretical privacy guarantees, validated by experiments showing 5.6% accuracy gains and 35.17% lower cold-start latency. Ablation studies validate its components effectiveness, and time-cost experiments confirm its enhanced recommendation efficiency. Overall, LDPTRec effectively balances recommendation security and efficiency while improving accuracy.

The backdoor attack has emerged as a prevalent threat that affects the effectiveness of machine learning models in intelligent vehicles. While such attacks may not impair the normal performance of the trained model, they can be exploited by malicious entities to manipulate model inferences, resulting in serious problems. In this paper, we design a dynamic gradient clipping (DGC) method aimed at rectifying backdoor models by eliminating the underlying backdoor trigger. Firstly, we construct a repair dataset fused by some clean samples and few-shot backdoor samples to amplify the backdoor behavior when we only obtain limited backdoor samples. Subsequently, we introduce sample states to characterize the backdoor behavior of the target model, determined by the model's inference outcome. Finally, we devise the DGC method to clip parameter gradients at varying degrees, effectively eliminating the backdoor trigger within the target model. Through the evaluation, the simulation results demonstrate that our DGC method exhibits robust defense capabilities against four contemporary state-of-the-art backdoor attacks, reducing the attack success rate by 95% with only$0.1\% \sim 4.8\%$model accuracy loss.

Edge storage presents a viable data storage alternative for application vendors (AVs), offering benefits such as reduced bandwidth overhead and latency compared to cloud storage. However, data cached in edge computing systems is susceptible to intentional or accidental disturbances. This paper proposes a decentralized integrity auditing scheme to safeguard data integrity and counter the traditional reliance on centralized third-party auditors (TPA), which are unfit for distributed systems. Our novel approach employs edge servers (ES) as mutual auditors, eliminating the need for a centralized entity. This decentralization minimizes potential collusion with malicious auditors and biases in audit outcomes. Using a strategic game model, we demonstrate that ESs are more motivated to audit each other than TPAs. The auditing process is addressed as a Nash Equilibrium problem, assuring accurate integrity proof through incentives for ESs. Our scheme's security and performance are rigorously assessed, showing it is secure within the random oracle model, offers improved speed, and is cost-effective compared to existing methods. It also significantly reduces computational and communication overhead.

Due to the robust representational capabilities of graph data, employing graph neural networks for its processing has demonstrated superior performance over conventional deep learning algorithms. Graph data encompasses abundant features and structural information; however, its large-scale collection is often challenging in practice. This difficulty arises because data predominantly exists in isolated compartments, making it arduous to harmonize information across various organizations or to enable multiple organizations to collaborate effectively while safeguarding local data privacy. In light of an extreme data distribution scenario, where each client possesses distinct nodes with partially overlapping segments yet divergent data features, we introduce a dual-cloud server architecture. This framework encompasses the design of four secure subprotocols: ReEnc (secure re-encryption), SecPSI (secure outsourcing of PSI), SecWeight (secure weight calculation), and SecAgg (secure aggregation). Together, these components facilitate a vertical federated learning framework for graph convolutional networks, ensuring privacy preservation. We provide a security proof for the entire system and extensive evaluation on three benchmark datasets (Cora, Citeseer, and Pubmed) illustrates that our Vertical Federated Graph Convolutional Network (VFGCN) surpasses existing privacy-preserving methodologies.

Crowdsensing has become a popular method of sensing data collection while facing the problem of protecting participants' location privacy. Existing location-privacy crowdsensing mechanisms focus on static tasks and participants without considering sensing tasks' time requirements and participants' mobility, which cannot achieve satisfactory collected data quality and task completion in crowdsensing with dynamic tasks and participants. Inspired by this, we proposed a location-preservation crowdsensing mechanism, FedSense, considering dynamic tasks and participants based on federated learning (FL) and reinforcement learning (RL). In FedSense, through RL's outstanding decision-making ability, participants select sensing tasks to perform by well-trained RL models without uploading location information to servers for task allocation. We propose an independent tasks selection environment that defines actions, states, and rewards of RL to enable FedSense to achieve satisfactory task completion and data quality while preserving location privacy. Besides, FedSense applies an asynchronous FL aggregation algorithm that reduces participants' network stabilization and device computing ability requirements. Analysis proves that participants' location information does not leave the local device during the model training and task selection process, effectively avoiding privacy leakage. Simulation shows that compared with existing location-preservation crowdsensing mechanisms, FedSense achieves the highest task completion and sensing accuracy for dynamic tasks and participants.

To motivate data owners’ (DOs’) trading willingness, the existing incentive mechanisms allow DOs to independently disturb data following data consumer's (DC’s) availability requirement. However, they cannot motivate DOs’ honest disturbance, which is attributed to DOs’ independent disturbance without any supervision. Thus, we implement an incentive mechanism for privacy preserved data trading with verifiable data disturbance where an honest-but-curious disturbance generator (DG) is additionally introduced to supervise DOs’ local disturbance and assist disturbance verification between DOs and DC. Specifically, DG generates the disturbance strategies and secretly distributes to DOs following private information retrieval, guaranteeing DOs's local disturbance's privacy and verifiability with our proposed three-level verification algorithm. Subsequently, we model the trading as a game and disturbance verification results determine the compensation and punishment for trading bilateral utilities following Nash Equilibrium where DOs honestly disturb data. Theoretical analysis shows that DOs are motivated to honestly disturb data and their raw data privacy is preserved. Extensive experiments using the real-world dataset demonstrate that the deviating DOs in our scheme can be verified with a probability of more than 90% and the statistical result accuracy can be improved by more than 80% compared with the existing works.

Federated learning (FL) is vulnerable to backdoor attacks due to its distributed nature. Existing unilateral defense mechanisms often fail against persistent attack strategies, primarily due to their limited perspectives. To address the challenge of model misclassification on the server side caused by overlooked model similarity drift, and gradient misjudgment on the client side caused by semantic learning imbalances across classes, this paper proposes a collaborative defense framework for federated learning, termed FL-CDF. FL-CDF establishes an end-to-end defense through a bidirectional client-server collaboration mechanism. Specifically: (1) On the client side, an adversarial perturbation-based malicious neuron detection module is introduced. This module measures neuron activation sensitivity by generating adversarial perturbations, and adaptively prunes backdoor neurons exhibiting high sensitivity. (2) On the server side, a multi-dimensional detection scheme is designed, which integrates neuron localization, adversarial sensitivity, and model parameters. By incorporating client-side feedback on malicious neurons, the server performs robust model aggregation. Theoretical analysis verifies the robustness of FL-CDF, and extensive experiments on public benchmarks demonstrate its effectiveness. In the best-case scenario, FL-CDF improves defense performance by 42.5% compared to current state-of-the-art (SOTA) defense.

Data confidentiality, a fundamental security element for dependable cloud storage, has been drawing widespread concern. Public-key encryption with keyword search (PEKS) has emerged as a promising approach for privacy protection while enabling efficient retrieval of encrypted data. One of the typical applications of PEKS is searching sensitive electronic medical records (EMR) in healthcare clouds. However, many traditional countermeasures fall short of balancing privacy protection with search efficiency, and they often fail to support multi-user EMR sharing. To resolve these challenges, we propose a novel lightweight multi-user public-key authenticated encryption scheme with keyword search (LM-PAEKS). Our design effectively counters the inside keyword guessing attack (IKGA) while maintaining the sizes of ciphertext and trapdoor constant in multi-user scenarios. The novelty of our approach relies on introducing a dedicated receiver server that skillfully transforms the complex many-to-many relationship between senders and receivers into a streamlined one-to-one relationship. This transformation prevents the sizes of ciphertext and trapdoor from scaling linearly with the number of participants. Our approach ensures ciphertext indistinguishability and trapdoor privacy while avoiding bilinear pairing operations on the client side. Comparative performance analysis demonstrates that LM-PAEKS features significant computational efficiency while meeting higher security requirements, positioning it as a robust alternative to existing solutions.

Reconstruction attacks against federated learning (FL) aim to reconstruct users’ samples through users’ uploaded gradients. Local differential privacy (LDP) is regarded as an effective defense against various attacks, including sample reconstruction in FL, where gradients are clipped and perturbed. Existing attacks are ineffective in FL with LDP since clipped and perturbed gradients obliterate most sample information for reconstruction. Besides, existing attacks embed additional sample information into gradients to improve the attack effect and cause gradient expansion, leading to a more severe gradient clipping in FL with LDP. In this paper, we propose a sample reconstruction attack against LDP-based FL with any target models to reconstruct victims’ sensitive samples to illustrate that FL with LDP is not flawless. Considering gradient expansion in reconstruction attacks and noise in LDP, the core of the proposed attack is gradient compression and reconstructed sample denoising. For gradient compression, an inference structure based on sample characteristics is presented to reduce redundant gradients against LDP. For reconstructed sample denoising, we artificially introduce zero gradients to observe noise distribution and scale confidence interval to filter the noise. Theoretical proof guarantees the effectiveness of the proposed attack. Evaluations show that the proposed attack is the only attack that reconstructs victims’ training samples in LDP-based FL and has little impact on the target model’s accuracy. We conclude that LDP-based FL needs further improvements to defend against sample reconstruction attacks effectively.

With the rapid growth of cloud storage technology, the demand for efficient and secure search of outsourced encrypted data has become increasingly critical. However, existing conjunctive keyword dynamic searchable encryption schemes often expose the Keyword Pair Result Pattern (KPRP) during index matching, compromising privacy. Additionally, frequent index updates require expensive group exponentiations, leading to high client-side overhead. To tackle these challenges, we propose LRP-HDSE, a lightweight dynamic conjunctive keyword searchable encryption scheme that hides KPRP while minimizing client computation costs. To enhance privacy, we introduce the Vector Hidden Subset Predicate Encryption (VH-SPE) mechanism, which enables the server to implicitly detect cross-tag in the membership matching index, effectively mitigating KPRP leakage. For improved efficiency, the scheme designs a lightweight membership matching index structure, LSet, based on low-cost multiset hash operations, reducing reliance on costly exponentiations and lowering client overhead. Our security analysis confirms that LRP-HDSE provides robust KPRP hiding along with forward and backward security in dynamic environments. Asymptotic analysis, along with experiment evaluations on two real-world datasets, show that our scheme offers superior client-side computational efficiency compared to existing approaches, making it both practical and effective.

Edge computing is conducive to reducing service response time and improving service quality by pushing cloud functions to a network's edges. Most existing works in edge computing focus on utility maximization of task offloading on static edges with a single antenna. Besides, trajectory planning of mobile edges, e.g., autonomous aerial vehicles (AAVs) is also rarely discussed. In this paper, we are the first to jointly discuss the deadline-ware task offloading and AAV trajectory planning problem in a multi-input multi-output (MIMO) AAV-aided mobile edge computing system. Due to discrete variables and highly coupling nonconvex constraints, we equivalently convert the original problem into a more solvable form by introducing auxiliary variables. Next, a penalty dual decomposition-based algorithm is developed to achieve a global optimal solution to the problem. Besides, we proposed a profit-based fireworks algorithm in a relatively lower time to reduce the execution time for large-scale networks. Extensive evaluation results reveal that our proposed optimal algorithms could significantly outperform static offloading algorithms and other algorithms by 25% on average.

Edge storage is becoming an increasingly appealing alternative for data owners (DOs), offering benefits like decreased latency and minimized bandwidth usage compared to traditional cloud storage solutions. Nonetheless, stored data within edge servers (ESs) remains vulnerable to disruptions. Existing data integrity auditing schemes face challenges such as the costs of third-party auditors (TPA), unreliable and delayed audit results, and effective management of data inspection concerning time and energy consumption. To tackle these challenges, we introduce DIVO, a decentralized data inspection approach. DIVO leverages ESs as each others’ auditors, removing the necessity for a centralized party, thereby mitigating collision risks and potential biases in audit results. We propose a game-theoretic technique to efficiently manage data inspection and verification offloading to ESs. By formulating the decision-making issue as a strategic game for optimally allocating verification tasks among multiple ESs, we establish the presence of Nash equilibrium and design a strategy to attain it. Through comprehensive security and performance evaluations, DIVO has been shown to operate securely within the random oracle model while delivering notable efficiency improvements over recent methods. Our analysis highlights that DIVO surpasses a wide range of recent approaches in both communication and computation efficiency.

As a fundamental service in mobile cloud computing, range query has attracted extensive attention. But the existing secure range query schemes not only leak data privacy but also have low query efficiency. To address those issues, we first design a novel range-matched code to convert the range query into code set matching, which aims to hide the order relationship of outsourced data as well as the index of most significant different bit. Based on the designed range-matched code, we propose aPractical andLess LeakageRangeQuery scheme over encrypted mobile cloud data (PLRQ) by integrating XOR filter and multiset hash function. Security analysis shows that PLRQ achieves semantic security and avoids data privacy leakage. Extensive experiments using real datasets demonstrate that, compared with two state-of-the-art solutions-RngMatch and LSRQ, our proposed PLRQ improves the query efficiency both by 2 orders of magnitude, and reduces the storage cost on Cloud Service Provider by about 79.5% and 73.6% respectively.

Collaborative searchable encryption for group data sharing enables a consortium of authorized users to collectively generate trapdoors and decrypt search results. However, existing countermeasures may be vulnerable to a keyword guessing attack (KGA) initiated by malicious insiders, compromising the confidentiality of keywords. Simultaneously, these solutions often fail to guard against hostile manufacturers embedding backdoors, leading to potential information leakage. To address these challenges, we propose a novel privacy-preserving collaborative searchable encryption (PCSE) scheme tailored for group data sharing. This scheme introduces a dedicated keyword server to export server-derived keywords, thereby withstanding KGA attempts. Based on this, PCSE deploys cryptographic reverse firewalls to thwart subversion attacks. To overcome the single point of failure inherent in a single keyword server, the export of server-derived keywords is collaboratively performed by multiple keyword servers. Furthermore, PCSE extends its capabilities to support efficient multi-keyword searches and result verification and incorporates a rate-limiting mechanism to effectively slow down adversaries' online KGA attempts. Security analysis demonstrates that our scheme can resist KGA and subversion attack. Theoretical analyses and experimental results show that PCSE is significantly more practical for group data sharing systems compared with state-of-the-art works.

Data is the essential fuel for deep neural networks (DNNs), and its quality affects the practical performance of DNNs. In real-world training scenarios, the successful generalization performance of DNNs is severely challenged by noisy samples with incorrect labels. To combat noisy samples in image classification, numerous methods based on sample selection and semi-supervised learning (SSL) have been developed, where sample selection is used to provide the supervision signal for SSL, achieving great success in resisting noisy samples. Due to the necessary warm-up training on noisy datasets and the basic sample selection mechanism, DNNs are still confronted with the challenge of memorizing noisy samples. However, existing methods do not address the memorization of noisy samples by DNNs explicitly, which hinders the generalization performance of DNNs. To alleviate this issue, we present a new approach to combat noisy samples. First, we propose a memorized noise detection method to detect noisy samples that DNNs have already memorized during the training process. Next, we design a noise-excluded sample selection method and a noise-alleviated MixMatch to alleviate the memorization of DNNs to noisy samples. Finally, we integrate our approach with the established method DivideMix, proposing Modified-DivideMix. The experimental results on CIFAR-10, CIFAR-100, and Clothing1M demonstrate the effectiveness of our approach.

Federated learning (FL) has become a popular mode of learning, allowing model training without the need to share data. Unfortunately, it remains vulnerable to privacy leakage and poisoning attacks, which compromise user data security and degrade model quality. Therefore, numerous privacy-preserving frameworks have been proposed, among which mask-based framework has certain advantages in terms of efficiency and functionality. However, it is more susceptible to poisoning attacks from malicious users, and current works lack practical means to detect such attacks within this framework. To overcome this challenge, we present DefendFL, an efficient, privacy-preserving, and poisoning-detectable mask-based FL scheme. We first leverage collinearity mask to protect users' gradient privacy. Then, cosine similarity is utilized to detect masked gradients to identify poisonous gradients. Meanwhile, a verification mechanism is designed to detect the mask, ensuring the mask's validity in aggregation and preventing poisoning attacks by intentionally changing the mask. Finally, we resist poisoning attacks by removing malicious gradients or lowering their weights in aggregation. Through security analysis and experimental evaluation, DefendFL can effectively detect and mitigate poisoning attacks while outperforming existing privacy-preserving detection works in efficiency.

With the popularity of blockchains, low transaction throughput has become a significant bottleneck in applications such as cryptocurrencies. Payment channel networks (PCNs) have received attention as a way to improve throughput. However, due to the difficulty of predicting future transactions for nodes, the transactions are prone to failure when the channel balances do not meet required conditions. It has been shown that increasing buffers (queues) in PCNs can increase the success rate of transactions and throughput. Nevertheless, there is no effective transaction scheduling strategy in buffers when transaction values are flexible and variable. To solve this problem, we first formulate the Scheduling Problem in PCNs (named PSP), and then prove it is NP-hard. We design a neural network solver based on the Sequence to Sequence (Seq2Seq) architecture and train the solver using the reinforcement learning method. With the solver, we first give two scheduling strategies to maximize transaction throughput, and then design a PCN simulator for performance evaluation. Extensive experiments are conducted to show the superiority and various performances of our proposal and illustrate that our proposal can get a significant advantage in terms of the transaction throughput compared to the existing works.

Deterministic Networking (DetNet) is a rising technology that offers deterministic delay & jitter and extremely low packet loss in large IP networks. To achieve determinism under failure scenarios, DetNet requires finding at least two paths with close end-to-end delay, i.e., adelay-diffconstraint, for mission-critical flows. However, how to find two routing paths subject to thedelay-diffconstraint remains open. We study the DetNet routing problem in two scenarios. First, given a primary path, we propose Pulse+, which finds a secondary path whose end-to-end delay is within a range determined by the end-to-end delay of the primary path and the delay-diff requirement. Second, we propose CoSE-Pulse+, which integrates Pulse+ with a divide-and-conquer approach to find a pair of paths that meet DetNet’s delay-diff constraint. Both Pulse+ and CoSE-Pulse+ guarantee solution optimality. Notably, although Pulse+ and CoSE-Pulse+ do not have a polynomial worst-case time complexity, their empirical solver running time is better than that of other algorithms. We evaluate Pulse+ and CoSE-Pulse+ against the K-Shortest-Path and Lagrangian-dual based algorithms using synthetic test cases generated over networks with up to 10000 nodes. Both Pulse+ and CoSE-Pulse+ can solve more test cases than other algorithms under a predefined time limit. Compared to the second best algorithm, Pulse+ achieves an average-time speedup of$5\times $and CoSE-Pulse+ achieves an average-time speedup of$22\times $. Our code and test cases are available athttps://gitee.com/zsz2019_shizhenzhao/drcr

Modern large-scale computing systems always demand better connectivity indicators for reliability evaluation. However, as more processing units have been rapidly incorporated into emerging computing systems, existing indicators (e.g.,$\ell$-component edge connectivity and$\ell$-extra edge connectivity) have gradually failed to provide the required fault tolerance. In addition, these indicators require, for example, that the faulty network should have at least$\ell$components (or that each component should have at least$\ell$nodes). These fault assumptions are not flexible enough to deal with diversified structural demands in practice circumstances. In order to address these challenges simultaneously, this article proposes two novel indicators for network reliability by utilizing the partition matroid technique, named matroidal connectivity and conditional matroidal connectivity. We first investigate the accurate values of (conditional) matroidal connectivity of$k$-ary$n$-cube$Q_{n}^{k}$, which is an appealing option as the underlying topology for modern parallel computing systems. Moreover, we propose an$O(k^{n-1})$algorithm for determining structural features of minimum edge sets whose cardinality is the conditional matroidal connectivity of$Q_{n}^{k}$. Simulation results are presented to verify our algorithm's correctness and further investigate the distribution pattern of edge sets subject to the restriction of partition matroid. We also present comparative analyses illustrating the superior edge fault tolerance of our findings in relation to prior research, which even exhibits an exponential enhancement when$k\geq 4$.

Since 2022, ChatGPT has been a big breakthrough in technology, creating lots of discussions online. It has had big effects in different areas, but in cybersecurity, it is both good and bad. There has been a lot of misuse, especially with squatting domains. Our research aims to understand this misuse and the potential threats it poses. We develop a novel method that looks at historical Passive DNS (PDNS) data. Based on the two-stage identification, our method can efficiently and accurately collect ChatGPT-related squatting domains. In the end, we found over 1.3 million ChatGPT-related squatting domains, part of which were shared with the security community. Our findings show that these squatting domains are increasing quickly. This is the case whether the keywords related to ChatG PT are registered with the domain registrar or set up on sub domains. Even though the number of domains is increasing, only 5.3 % set up meaningful content on their websites. After digging into their web contents, we found that these web sites show various signs of misuse, such as promotion on illegal underground websites and emerging fraudulent activities related to dialogue features. The security community is not fully aware of these threats yet. We are the first to conduct a large-scale quantitative analysis of ChatGPT-related abusive behavior. We believe that our work unveils the abuse ecosystem surrounding ChatGPT-related squatting domains. We hope to underscore the urgent need for increased attention and protective measures against ChatGPT-related domain abuse.

Biometrics is a technology that utilizes individual physiological or behavioral characteristics for identity authentication and identification, ensuring secure and accurate identity verification by comparing biometric information with samples in a database. However, traditional biometric technology raises concerns about privacy leakage, which has led to the emergence of privacy-preserving biometric technology. This study introduces a cloud-assisted privacy-preserving biometric authentication system based on multi-key full homomorphic encryption. Our scheme employs a TFHE encryption scheme to encrypt user biometrics and utilizes a cloud server to assist in computation. We design secure computing protocols based on multi-key TFHE and develop a privacy-preserving biometric system based on a single cloud server. Privacy analysis and performance evaluation demonstrate that the proposed solution is efficient and feasible. Our experimental findings indicate that the proposed scheme exhibits a superior accuracy rate to current schemes. Compared to the best solution, our method has increased the iris recognition accuracy by approximately 68.42%. Although the experimental results demonstrate high accuracy and feasibility, implementing TFHE in biometric models could be improved by its execution time, presenting challenges for broad adoption. Nevertheless, through optimization and technological advancements, this protocol is anticipated to elevate privacy protection standards in practical biometric recognition systems moving forward.

Truth discovery is an effective tool for discovering the truth from a multitude of data points of varying quality, which inherently involves privacy concerns. While existing studies have predominantly focused on protecting workers’ submitted sensing data using local differential privacy (LDP), they overlook a crucial aspect of real-world scenarios: workers are likely to provide more accurate data for tasks they perceive as important, resulting in submissions that more closely approximate the truth for these tasks. Moreover, the prevalent use of the Laplace mechanism for noise addition, due to the inherent randomness and unboundedness of the Laplace distribution, might lead to excessive noise, potentially compromising the accuracy of truth discovery and yielding a noisy approximation of the truth. To address these limitations, we propose a Gaussian distribution-based truth discOvery approach under Local Differential privacy (GOLD). The algorithm’s core innovation lies in its comprehensive utilization of Gaussian distribution for both task importance and worker quality after adding Laplacian noise. Workers first apply Laplacian noise to their data locally, after which the problem is formalized as a constraint optimization task, deriving an iterative equation for the noisy truth. Theoretical analysis demonstrates that the GOLD algorithm rigorously adheres to local differential privacy requirements while achieving high truth accuracy and low time complexity. Empirical validation on two real datasets reveals that, compared to state-of-the-art algorithms, the GOLD algorithm improves the truth accuracy by at least 20%.

Task allocation, a core component of mobile crowd-sensing systems, facilitates the collection, analysis, and sharing of diverse data. While existing studies often employ planar Laplacian (PL) distribution to achieve Geo-indistinguishability (Geo-I) for worker location protection, the randomness and boundlessness of PL distribution, coupled with greedy allocation strategies, often lead to excessive noise and incomplete task assignments. Moreover, these approaches typically overlook the equilibrium between worker and server benefits. To address these challenges under Geo-I, we present the Kitty approach, which adopts Q-learning to achieve superior task allocation after formalizing a constrained optimization problem that maximizes profits for both parties. Kitty operates through three key mechanisms: 1) formalizing a constrained optimization problem based on a comprehensive analysis of both parties’ profits and a pre-defined equilibrium parameter, 2) implementing adaptive adjustment of the Q-learning greedy parameter to balance exploration and exploitation, and 3) designing two conflict resolution strategies to mitigate potential distance conflicts after location perturbation. Experiments on two real-world datasets demonstrate that Kitty outperforms the state-of-the-art by at least 15% in average travel distance reduction and 1% in task completion rate improvement.

Self-ensemble adversarial training methods improve model robustness by ensembling models at different training epochs, such as model weight averaging (WA). However, previous research has shown that self-ensemble defense methods in adversarial training (AT) still suffer from robust overfitting, which severely affects the generalization performance. Empirically, in the late phases of training, the AT becomes more overfitting to the extent that the individuals for weight averaging also suffer from overfitting and produce anomalous weight values, which causes the self-ensemble model to continue to undergo robust overfitting due to the failure in removing the weight anomalies. To solve this problem, we aim to tackle the influence of outliers in the weight space in this work and propose an easy-to-operate and effective Median-Ensemble Adversarial Training (MEAT) method to solve the robust overfitting phenomenon existing in self-ensemble defense from the source by searching for the median of the historical model weights. Experimental results show that MEAT achieves the best robustness against the powerful AutoAttack and can effectively allievate the robust overfitting. We further demonstrate that most defense methods can improve robust generalization and robustness by combining with MEAT.

Graph neural networks (GNNs) have been widely applied in various graph analysis tasks. To provide more convenient and faster predictive services, many enterprises are choosing to deploy GNNs in cloud environments. However, given the increasing privacy concerns about GNNs models and graph data, as well as the need to quickly generate embeddings for new nodes in real-world applications, a critical issue in this emerging paradigm is to ensure the security and scalability of GNN predictions. In this paper, we propose a privacy-preserving and scalable GNN prediction scheme, named PS-GNN, to address the privacy issues in cloud environments. Specifically, PS-GNN utilizes a customized array structure to store graph data and employs secret sharing to preserve the confidentiality of both the GNN model and graph data. Besides, the scalability of PS-GNN is achieved by aggregating feature information from local node neighborhoods in parallel. Through a detailed analysis, we demonstrate the security of PS-GNN. Extensive experiments on real-world datasets demonstrate that PS-GNN outperforms existing schemes in terms of computational and communication overhead, and reaches state-of-the-art performance on large graphs.

Federated Learning (FL) enables multiple clients to collaborate in training neural network models while retaining their private data locally. Despite its advantages, FL is vulnerable to backdoor attacks due to its distributed nature. Attackers introduce triggers into the global model, causing it to make specified predictions on inputs containing these triggers. Existing detection or clustering defense methods based on distance and similarity have significant limitations. Methods based on clipping and adding noise can only slightly mitigate the impact of backdoor attacks. To achieve a better defense, we introduce FedCL, a backdoor defense framework that accurately detects backdoor models by assessing the uncertainty of model predictions. Additionally, it employs dynamic clipping to limit model updates’ impact, successfully mitigating backdoor attacks without compromising the global model’s accuracy. The experiments indicate that FedCL moderately improves by 0.01%↑ ∼ 85.78%↑ than the state-of-the-art (SOTA) defense methods, especially in the CIFAR-10 task trained with more complex networks.

Abnormal email bounces seriously disrupt user lives and company transactions. Proliferating security protocols and protection strategies have made email delivery increasingly complex. A natural question is how and why email delivery fails in the wild. Filling this knowledge gap requires a representative global email delivery dataset, which is rarely disclosed by email service providers (ESPs).

Adversarial examples (AEs), which are maliciously hand-crafted by adding perturbations to benign images, reveal the vulnerability of deep neural networks (DNNs) and have been used as a benchmark for evaluating model robustness. With great efforts have been devoted to generating AEs with stronger attack ability, the visual quality of AEs is generally neglected in previous studies. The lack of a good quality measure of AEs makes it very hard to compare the relative merits of attack techniques and is hindering technological advancement. How to evaluate the visual quality of AEs remains an understudied and unsolved problem. In this work, we make the first attempt to fill the gap by presenting an image quality assessment method specifically designed for AEs. Towards this goal, we first construct a new database, called AdvDB, developed on diverse adversarial examples with elaborated annotations. We also propose a detection-based structural similarity index (AdvDSS) for adversarial example perceptual quality assessment. Specifically, the visual saliency for capturing the near-threshold adversarial distortions is first detected via human visual system (HVS) techniques and then the structural similarity is extracted to predict the quality score. Moreover, we further propose AEQA for overall adversarial example quality assessment by integrating the perceptual quality and attack intensity of AEs. Extensive experiments validate that the proposed AdvDSS achieves state-of-the-art performance which is more consistent with human opinions.

With the growing diversity of data sources, multi-view learning methods have attracted considerable attention. Among these, by modeling the multi-view data as multi-view graphs, multi-view Graph Neural Networks (GNNs) have shown encouraging performance on various multi-view learning tasks. The message passing is the critical mechanism empowering GNNs with superior capacity to process complex graph data. However, most multi-view GNNs are designed on the well-established overall framework, overlooking the intrinsic challenges of the message passing on multi-view scenarios. To clarify this, we first revisit the message passing mechanism from a Laplacian smoothing perspective, revealing the key to designing a multi-view message passing. Following the analysis, in this paper, we propose an enhanced GNN framework termed Confluent Graph Neural Networks (CGNN), with Cross-view Confulent Message Pssing (CCMP) tailored for multi-view learning. Inspired by the optimization of an improved multi-view Laplacian smoothing problem, CCMP contains three sub-modules that enable the interaction between graph structures and consistent representations, which makes it aware of consistency and complementarity information across views. Extensive experiments on four types of data including multi-modality data demonstrate that our proposed model exhibits superior effectiveness and robustness. The code is available at https://github.com/shumanzhuang/CGNN.

Traffic Engineering (TE) is critical for improving network performance and reliability. A key challenge in TE is the management of sudden traffic bursts. Existing TE schemes either do not handle traffic bursts or uniformly guard against traffic bursts, thereby facing difficulties in achieving a balance between normal-case performance and burst-case performance. To address this issue, we introduce FIGRET, a Fine-Grained Robustness-Enhanced TE scheme. FIGRET offers a novel approach to TE by providing varying levels of robustness enhancements, customized according to the distinct traffic characteristics of various source-destination pairs. By leveraging a burst-aware loss function and deep learning techniques, FIGRET is capable of generating high-quality TE solutions efficiently. Our evaluations of real-world production networks, including Wide Area Networks and data centers, demonstrate that FIGRET significantly outperforms existing TE schemes. Compared to the TE scheme currently deployed in Google's Jupiter data center networks, FIGRET achieves a 9%-34% reduction in average Maximum Link Utilization and improves solution speed by 35×-1800×. Against DOTE, a state-of-the-art deep learning-based TE method, FIGRET substantially lowers the occurrence of significant congestion events triggered by traffic bursts by 41%-53.9% in topologies with high traffic dynamics.

Web Application Firewalls (WAFs) are a crucial line of defense against web-based attacks. However, an emerging threat comes from protocol-level evasion vulnerabilities, in which adversaries exploit parsing discrepancies between the WAF HTTP parser and those of web applications to circumvent WAFs. Currently, uncovering these vulnerabilities still depends on manual, ad hoc methods. In this paper, we propose WAF Manis, a novel testing methodology to automatically discover protocol-level evasion vulnerabilities in WAFs. We evaluated WAF Manis against 14 popular WAFs including Cloudflare and ModSecurity and 20 popular web frameworks including Laravel and Spring. In total, we discovered 311 protocol-level evasion cases affecting all tested WAFs and applications. Due to the generic nature of protocol-level evasions, these evasion vulnerabilities do not hinge on specific payload patterns and can transmit any malicious payloads - for instance, SQL injection, XSS, or Log4jShell - to the target websites. We further analyzed these vulnerabilities and identified three primary reasons contributing to WAF evasions. We have reported those identified vulnerabilities to the affected providers and received acknowledgments and bug bounty rewards from Cloudflare WAF, Fortinet WAF, Alibaba Cloud WAF, Huawei Cloud WAF, ModSecurity, Go security Team, and the PHP security team.

Ensuring data integrity and confidentiality is critical in communication systems. Traditional methods, such as separate encryption and signature schemes, often lead to inefficiencies. While signcryption methods address both needs simultaneously, they are inadequate for data outsourcing systems like cloud computing due to the requirement for original files during data verification. Conversely, remote data integrity checking (RDIC) methods eliminate the need for original files but lack confidentiality. This article fills the gap in cloud security by introducing remote signcryption (RSC) and presenting the first concrete RSC scheme. We demonstrate the application of this novel approach in cloud-assisted Internet of Things (IoT) networks. Our work includes defining the security for an RSC scheme and proving its security under the bilinear Diffie-Hellman (BDH) hardness assumption. Implementing our proposed scheme on real data from trending YouTube video statistics, we found that RSC significantly outperforms existing methods, achieving 100 times faster speed and reducing communication costs by half compared to RDIC methods. Notably, even with 5 MB of outsourced data, RSC keeps the communication cost under 8 kB during data recovery, a substantial improvement over classical signcryption methods that require over 5 MB.

With the widespread growth of cloud computing technology, cloud software services are ubiquitous these days. Using this technology, software providers can sell their products through cloud computing environments in the pay-as-you-use fashion. However, performing secure and accurate calculations in cloud computing environments has become extremely challenging. As the data to be processed by cloud software might be highly sensitive, its confidentiality needs to be taken care of before transferring the data to the cloud server. Also, in addition to the data confidentiality, the security of algorithms employed in the software is of vital importance, and thus software owners may be worried about revealing their algorithms through the cloud server. Homomorphic cryptosystems can provide confidentiality for data to be processed online. However, the confidentiality of algorithms is still an open problem. To address this issue, we put forward a privacy-preserving joint data and function homomorphic encryption (JDF-HE) mechanism. Our JDF-HE can provide confidentiality for both algorithms and data, thereby being suitable for cloud software services. We prove the security of JDF-HE and analyze its performance by evaluating its actual execution overhead. Our performance and security analysis demonstrate that JDF-HE is secure and suitable for real-time applications.

Privacy-preserving truth discovery, as a data aggregation algorithm that can extract reliable results from disparate and conflicting data in a privacy-preserving manner, has received a lot of attention in ensuring the reliability and privacy of data in mobile crowdsensing systems. However, most of the existing work requires that workers must stay online all the time during the full process of truth discovery. Although a few recent schemes have been proposed to tolerate worker dropout, they are tailored for a single-round setting. Repeating these schemes several times to adapt to the truth discovery will introduce significant computational and communication overheads, especially for the workers. To solve the above challenges, in this paper, we propose a multi-round efficient and secure truth discovery scheme in mobile crowdsensing systems that can balance the 3-way trade-off between privacy protection, dropout tolerance, and protocol efficiency. Specifically, we devise a novel mask generation capable of reusing secrets to eliminate the costly overhead of workers needing to recompute new secrets each round. Besides, we design a lightweight dropout tolerance mechanism to guarantee that even if workers drop out halfway, the server can still acquire meaningful truth. Rigorous security analysis and extensive experimental results demonstrate the privacy and efficiency of our scheme, respectively.

In cloud-based health monitoring services, healthcare centers often outsource support vector machine (SVM)-based clinical decision models to provide remote users with clinical decisions. During service provisioning, authorized external organizations like insurance companies aim to verify decision correctness to prevent fraudulent medical reimbursements. However, existing verifiable and secure SVM classification schemes have predominantly focused on user self-verification, thereby introducing potential risks of privacy leakage (such as input data exposure) in publicly verifiable scenarios. To address the aforementioned limitation, we propose a publicly verifiable and secure SVM classification scheme (PVSSVM) for cloud-based health monitoring services in a malicious setting, which can accommodate the verification needs of users or authorized external organizations with respect to potential malicious results returned by cloud servers. Specifically, we utilize homomorphic encryption and secret sharing to protect the model and data confidentiality in the cloud server, respectively. Based on a multiserver verifiable computation framework, PVSSVM achieves public verification of predicted results. Additionally, we further investigate its performance. Experimental evaluations demonstrate that PVSSVM outperforms existing state-of-the-art solutions in terms of computation and communication overhead. Notably, in the verification scenario of large-scale predictions, the proposed scheme achieves a reduction of approximately 83.71% in computation overhead through batch verification, as compared to one-by-one verification.

Active learning (AL) tries to maximize the model’s performance when the labeled data set is limited, and the annotation cost is high. Although it can be efficiently implemented in deep neural networks (DNNs), it is questionable whether the model can maintain the ability to generalize well when there are significant distributional deviations between the labeled and unlabeled data sets. In this article, we consider introducing adversarial training and adversarial samples into AL to mitigate the problem of degraded generalization performance due to different data distributions. In particular, our proposed adversarial training AL (ATAL) has two advantages, one is that adversarial training by different networks enables the network to have better prediction performance and robustness with limited labeled samples. The other is that the adversarial samples generated by the adversarial training can effectively expand the labeled data set so that the designed query function can efficiently select the most informative unlabeled samples based on the expanded labeled data set. Extensive experiments have been performed to verify the feasibility and efficiency of our proposed method, i.e., CIFAR-10 demonstrates the effectiveness of our method—new state-of-the-art robustness and accuracy are achieved.

In the era of the Internet of Things (IoT), the rapid development of cloud computing has been advancing location-based services (LBS). To enjoy the considerable advantages of lower cost and higher performance of cloud computing, it has become the first choice for most IoT enterprises to outsource data and services to public clouds. However, the privacy protection of data and the integrity of query results cannot be effectively guaranteed since public clouds cannot be fully trusted. In this paper, we propose a lightweight verifiable range query scheme (namely VeriRange). First, a pair of mutually perpendicular locality-sensitive hashing (LSH) is adopted to divide the original geographic data into subsets. Then a pivoted k dimensional (PKD) tree and a height-balanced binomial search tree (i.e., AVL tree) are established on the client and the cloud respectively to accelerate the processes of queries. To ensure the verification of query results, a keyed hash function is utilized to generate a verification tag for each subset. Verification tags in the public cloud are encrypted and independent of queries. It ensures fast verification of query results because the verification tags are not repeatedly calculated on each query. Formal security analysis shows VeriRange ensures the privacy of data, queries, and results. Experimental studies were conducted on real and synthetic datasets and demonstrated that the query and verification time in VeriRange is almost 2-3 orders of magnitude faster than that in state-of-art schemes.

The rapid development of the Artificial Intelligence of Things (AIoT) opens up a new perspective for emerging service-based applications and becomes a major driver of diverse federated learning (FL) applications. However, due to the heterogeneity of nodes and the existence of free-rider attacks, some device nodes may launch free-rider attacks to obtain the global model without any contribution, which not only dampens the enthusiasm of legitimate participants but also undermines the fairness of node contributions. In this article, we propose a free-rider attack detection (FRAD) mechanism for FL with deep autoencoding Gaussian mixture model (DAGMM) based on contribution and reputation. Specifically, we first model the contribution values based on the computing resource, communication cost, and data quality of each device node. Then, based on PageRank algorithms, we design an optimal reputation-based model to fairly and precisely choose benign nodes to participate in federated training under information asymmetry. Furthermore, we develop the FRAD mechanism via DAGMM that combines historical contribution with reputation scores. Simulation results validate that the proposed mechanism in this article outperforms the state-of-the-art baselines$(\sim \!\! 2.14\times $and$\sim \!\! 1.1\times $on MNIST and CIFAR, respectively) in defending against free-rider attacks, and when the main clients are free-riders, i.e., 50% or even up to 80% of the free-riders, FRAD can still maintain a high defense performance against free-rider attacks.

With the development of deep learning, people are more and more concerned about the security of data. Federated learning can solve the problem of data island, but it also brings more serious data privacy problems. Furthermore, in the process of multisource data collaboration, the efficiency of the whole federated learning system is usually not high. In this article, we introduce a scheme named FVFL, which ensure the local data security and resistance to collusive attacks, more importantly it can well support client flexible participate federated learning. We adopt Paillier encryption and secret sharing to guarantee client’s data security and resistance to collusive attacks. Moreover, our encryption mechanism allows client to participate in federated learning flexibly, and the correctness of the encryption algorithm is not affected by client’s drop out. The super-increasing sequence is introduced to reduce the communication overhead of the whole system, the simulation result shows that the result is significant; the Lagrange interpolation polynomial and secret Sharing is introduced to implement verification mechanism, to prevent malicious forgery of aggregation results in the cloud. The verification mechanism ensures the clients to obtain real and reliable aggregation results in the cloud. Moreover, our verification mechanism allows client to participate in federated learning flexibly, and the correctness of the verification algorithm is not affected by client’s drop out. And the experimental results show that FVFL has high accuracy and efficiency.

In this article, we propose a secure fine-grained task allocation scheme with bilateral access control (FTA-BAC) for intelligent transportation systems. To enhance the security, we formulate bilateral access control in task allocation, by adopting the matchmaking encryption (ME) to encrypt the task requirements/interests for secure task matching. In this way, both task requesters and workers can specify their match policies simultaneously, without revealing their sensitive information (i.e., attributes and geographical location). To realize fine-grained task allocation, we use a linear integer secret sharing (LISS) scheme to represent task requirements/interests, supporting theAND/ORoperation on match policies. To further improve the efficiency, we design a delegation mechanism to reduce the computation burden on resource-limited end devices, by diverting the high-frequency matching operations to edge nodes. Then, we prove the security of FTA-BAC under formally defined security model. Finally, we analyze the performance of FTA-BAC through theoretical analysis and experimental evaluation, demonstrating that FTA-BAC can provide practical task allocation for intelligent transportation systems compared with the state-of-the-art works.

The health-related Internet of Things (IoT) play an irreplaceable role in the collection, analysis, and transmission of medical data. As a device of the health-related IoT, the electroencephalogram (EEG) has long been a powerful tool for physiological and clinical brain research, which contains a wealth of personal information. Due to its rich computational/storage resources, cloud computing is a promising solution to extract the sophisticated feature of massive EEG signals in the age of big data. However, it needs to solve both response latency and privacy leakage. To reduce latency between users and servers while ensuring data privacy, we propose a privacy-preserving feature extraction scheme, called LightPyFE, for EEG signals in the edge computing environment. In this scheme, we design an outsourced computing toolkit, which allows the users to achieve a series of secure integer and floating-point computing operations. During the implementation, LightPyFE can ensure that the users just perform the encryption and decryption operations, where all computing tasks are outsourced to edge servers for specific processing. Theoretical analysis and experimental results have demonstrated that our scheme can successfully achieve privacy-preserving feature extraction for EEG signals, and is practical yet effective.

Attribute-based searchable encryption (ABSE) is a promising encryption mechanism for sharing outsourced encrypted data in clouds, allowing fine-grained access control over data while searching for encrypted data. However, the access policy in the most existing ABSE schemes exists in plaintext, which could expose sensitive information about legitimate data users. Moreover, such schemes delegate complex search operations to a cloud server, which can lead to data tampering and even untrusted results, and single point of failure. In this article, we propose a blockchain (BC)-based anonymous ABSE scheme for data sharing (BADS). First, attributes of the access policy are hidden, thus, providing confidentiality to the set of attributes that satisfy the access policy. Then combining ABSE with BC have features of tamper-proof, integrity verification, and nonrepudiation. In particular, information, such as secure index is stored in BC, while encrypted data is stored in a distributed system called the interplanetary file system (IPFS) to avoid single point of failure. Finally, BADS supports the matching algorithm that perform a fixed number of pairing operations before searching algorithm. We analysis security and evaluate performance to show the efficiency and practicability of BADS.

Decentralized identity (DID) systems conforming to the World Wide Web Consortium (W3C) Decentralized Identifiers (DIDs) and Verifiable Credentials Data Model recommendations have recently attracted attention due to their better autonomy, interoperability, and openness design. However, those W3C recommendations lack a design for addressing the single point of failure (SPOF) and identity revocation, which could seriously compromise the robustness and practicality of DID systems. To remedy these limitations, we propose FutureDID, a DID system that enables multiple parties to jointly issue credentials and efficiently revoke DID identities, providing a robust and practical DID system. FutureDID is designed with a multi-party credential issuing mechanism based on distributed key generation technology, which transforms trust from a single entity to distributed committees and facilitates authentication between issuers, making it more resistant to SPOF. Moreover, the underlying blockchain system is built on a chameleon hash function to ensure tamper-proof and enable efficient identity revocation. We have implemented a prototype system using FISCO BCOS and conducted extensive evaluations to demonstrate the effectiveness and practicality of our system. Our evaluations have shown that FutureDID provides a significant improvement in efficiency, achieving at least a 60 × efficiency improvement in identity revocation compared to state-of-the-art systems.

Deep Convolution Neural Networks (CNNs) have become the cornerstone of image classification, but the emergence of adversarial image attacks brings serious security risks to CNN-based applications. As a local perturbation attack, the border attack can achieve high success rates by only modifying the pixels around the border of an image, which is a novel attack perspective. However, existing border attacks have shortcomings in stealthiness and are easily detected. In this article, we propose a novel stealthy border attack method based on deep feature alignment. Specifically, we propose a deep feature alignment algorithm based on style transfer to guarantee the stealthiness of adversarial borders. The algorithm takes the deep feature difference between the adversarial and the original borders as the stealthiness loss and thus ensures good stealthiness of the generated adversarial images. To ensure high attack success rates simultaneously, we apply cross entropy to design the targeted attack loss and use margin loss as well as Leaky ReLU to design the untargeted attack loss. Experiments show that the structural similarity between the generated adversarial images and the original images is 8.8% higher than the state-of-art border attack method, indicating that our proposed adversarial images have better stealthiness. At the same time, the success rate of our attack in the face of defense methods is much higher, which is about four times that of the state-of-art border attack under the adversarial training defense.

Due to enormous computing and storage overhead for well-trained Deep Neural Network (DNN) models, protecting the intellectual property of model owners is a pressing need. As the commercialization of deep models is becoming increasingly popular, the pre-trained models delivered to users may suffer from being illegally copied, redistributed, or abused. In this paper, we propose DeepDIST, the first end-to-end secure DNNs distribution framework in a black-box scenario. Specifically, our framework adopts a dual-level fingerprint (FP) mechanism to provide reliable ownership verification, and proposes two equivalent transformations that can resist collusion attacks, plus a newly designed similarity loss term to improve the security of the transformations. Unlike the existing passive defense schemes that detect colluding participants, we introduce an active defense strategy, namely damaging the performance of the model after the malicious collusion. The extensive experimental results show that DeepDIST can maintain the accuracy of the host DNN after embedding fingerprint conducted for true traitor tracing, and is robust against several popular model modifications. Furthermore, the anti-collusion effect is evaluated on two typical classification tasks (10-class and 100-class), and the proposed DeepDIST can drop the prediction accuracy of the collusion model to 10% and 1% (random guess), respectively.

Federated learning is widely used and researched as an effective method for solving the privacy problems faced by centralized learning. To address the communication limitations and heterogeneity among clients, many existing methods based on the mixup algorithm share data mixed with the client’s local dataset to improve the model accuracy. However, due to the heterogeneity of federated learning, there may be some clients who join the mixup process with insufficient data, which will violate the privacy-preserving assumption of the mixup. Because of this weakness, many methods based on the mixup approach will face a serious privacy problem while trying to improve federated learning over other parts, e.g., accuracy or communication efficiency. Therefore, we propose the FedMDO framework to solve the privacy problem faced by mixup-based methods. In FedMDO, we introduce the auxiliary client to hold the auxiliary dataset that is related to the federated learning task and to generate the mixup templates for clients to increase the amount of data in the mixup process. By introducing the auxiliary client, the decrease in model accuracy can be suppressed as much as possible while taking advantage of the privacy-preserving gain from the increase in data volume. Furthermore, we introduce differential privacy into FedMDO with an elaborate redesign to enhance privacy protection. The corresponding analysis shows that under FedMDO, differential privacy can achieve the same protection with less negative impact. Experiments show that with at least an approximately 10%+ improvement in model accuracy and an average of 5 times greater communication savings compared to the FedAvg and non-IID SOTAs with weak privacy protection design, our method can yield significant improvement in the privacy of the shared data.

Evolutionary algorithms (EAs), such as the genetic algorithm (GA), offer an elegant way to handle combinatorial optimization problems (COPs). However, limited by expertise and resources, most users lack the capability to implement EAs for solving COPs. An intuitive and promising solution is to outsource evolutionary operations to a cloud server, however, it poses privacy concerns. To this end, this article proposes a novel computing paradigm called evolutionary computation as a service (ECaaS), where a cloud server renders evolutionary computation services for users while ensuring their privacy. Following the concept of ECaaS, this article presents privacy-preserving genetic algorithm (PEGA), a privacy-preserving GA designed specifically for COPs. PEGA enables users, regardless of their domain expertise or resource availability, to outsource COPs to the cloud server that holds a competitive GA and approximates the optimal solution while safeguarding privacy. Notably, PEGA features the following characteristics. First, PEGA empowers users without domain expertise or sufficient resources to solve COPs effectively. Second, PEGA protects the privacy of users by preventing the leakage of optimization problem details. Third, PEGA performs comparably to the conventional GA when approximating the optimal solution. To realize its functionality, we implement PEGA falling in a twin-server architecture and evaluate it on two widely known COPs: 1) the traveling Salesman problem (TSP) and 2) the 0/1 knapsack problem (KP). Particularly, we utilize encryption cryptography to protect users' privacy and carefully design a suite of secure computing protocols to support evolutionary operators of GA on encrypted chromosomes. Privacy analysis demonstrates that PEGA successfully preserves the confidentiality of COP contents. Experimental evaluation results on several TSP datasets and KP datasets reveal that PEGA performs equivalently to the conventional GA in approximating the optimal solution.

Cloud auditing allows users to leverage digital signature evidences to undertake remote data verification and consequently determine the integrity of their data stored in the cloud. While there are many cloud auditing schemes proposed for cloud services, deployments on large scale smart grid (SG) are known to be challenging in practice, for example in terms of inefficiency and lack of robustness. In this paper, we propose an efficient and robust cloud auditing scheme for SG (hereafter referred to as SG-Audit). Specifically, we utilize mobile edge computing (served as proxy signer) to offload the signature computation loads incurred by smart meters (SMs), as well as devising an efficient proxy signer recommendation strategy to ensure each SM obtains high quality service, a scalable index structure to reduce the signature evidence access time during data verification, and a deduplication and sampling based challenge data index generation strategy to narrow down the verification scope. Moreover, we also define three strategic threat scenarios supported by SG-Audit, and further devise a secure cloud auditing protocol to improve robustness. Through rigorous mathematical analysis and extensive experiments, we demonstrate that SG-Audit achieves increased auditing efficiency (by about 42% on average) in comparison to prior work.

Federated Learning (FL) is widely used in various industries because it effectively addresses the predicament of isolated data island. However, eavesdroppers is capable of inferring user privacy from the gradients or models transmitted in FL. Homomorphic Encryption (HE) can be applied in FL to protect sensitive data owing to its computability over ciphertexts. However, traditional HE as a single-key system cannot prevent dishonest users from intercepting and decrypting the ciphertexts from cooperative users in FL. Guaranteeing privacy and efficiency in this multi-user scenario is still a challenging target. In this paper, we propose a secure and efficient Federated Learning scheme (SecFed) based on multi-key HE to preserve user privacy and delegate some operations to TEE to improve efficiency while ensuring security. Specifically, we design the first TEE-based multi-key HE cryptosystem (EMK-BFV) to support privacy-preserving FL and optimize operation efficiency. Furthermore, we provide an offline protection mechanism to ensure the normal operation of system with disconnected participants. Finally, we give their security proofs and show their efficiency and superiority through comprehensive simulations and comparisons with existing schemes. SecFed offers a 3x performance improvement over TEE-based scheme and a 2x performance improvement over HE-based solution.

Hierarchical trees are widely used in differentially private statistical releases. Existing fast specialized algorithms guarantee hierarchical consistency but not non-negativity, which may incur meaningless negative values due to randomness. Quadratic programming can achieve optimally non-negative consistent releases, but traditional numerical-based methods face significant performance challenges when handling large-scale hierarchical trees. In this article, we construct the element set of Lagrange multiplier coefficients$\mathcal {K}$that satisfy the first type of KKT condition (values$\geq 0$and gradients$= 0$). Applying Generation Matrix, we find that meticulously constructing an unconstrained set$\mathcal {S} \subseteq \mathcal {K}$, we can further find a larger$\mathcal {S} \subseteq \mathcal {K}$until$\mathcal {S} = \mathcal {K}$, as demonstrated in our proof (we also term this as the Unconstrained Set Expansion Theorem). Based on the theorem, we design an efficient Generation Matrix-based optimally non-negative consistent release algorithm (GMNC), which can easily handle large-scale hierarchical trees with more than 100 million nodes. Our experiments show that GMNC has an extremely high iteration efficiency with no more than 20 (only$2\sim 8$on average) iterations even in the worst case. Compared to Interior Point Convex Method, GMNC improves the data scale processing limit up to 33.4 times in our experimental environment while requiring only 0.7% of the running time.

Federated learning (FL) provides a learning framework without participants sharing local raw data, but individual privacy is still at risk of disclosure through attacking the trained models. Due to the strong privacy guarantee, differential privacy (DP) is widely applied to FL to avoid privacy leakage. Traditional private learning adds noise directly to the gradients. The continuous accumulated noise on parameter models severely impairs learning effectiveness. To solve this problem, we introduce the idea of differentially private continuous data release (DPCR) into FL and propose an FL framework based on DPCR (FL-DPCR). Meanwhile, our proposed Equivalent Aggregation Theorem demonstrates that DPCR effectively reduces the overall error added to parameter models and improves FL's accuracy. To improve FL-DPCR's learning effectiveness, we introduce Matrix Mechanism to construct a release strategy and design a binary-indexed-tree (BIT) based DPCR model for Gaussian mechanism (BCRG). By solving a complex nonlinear programming problem with negative exponents, BCRG achieves optimal release accuracy efficiently. Besides, we exploit the residual privacy budget to boost the accuracy further and propose an advanced BCRG version (ABCRG). Our experiments show that, compared to traditional FL with DP, our achievements improve the accuracy with gains ranging from$3.4\%$on FMNIST to$65.7\%$on PAMAP2.

Advanced Persistent Threats (APTs) employ sophisticated and covert tactics to infiltrate target systems, leading to increased vulnerability and an elevated risk of exposure. Consequently, it is essential for us to proactively create an extensive and clearly outlined attack chain for APTs in order to effectively combat these threats. Unlike traditional malware or application threats, APTs can sidestep cyber security efforts and cause severe damage to organizations or even state security. Nonetheless, earlier methods struggle to accurately track APTs and may face a dependency explosion issue, as identifying the intricate and complex unknown malicious activities within APTs proves to be challenging. In this paper, we propose and build an approach, T-trace, which constructs the events provenance graphs by analyzing the correlations among logs. The approach precisely finds the log communities with tensor decomposition and calculates significance scores to extract the events. The APTs can be inferred by discovering the event communities and constructing the provenance graph with log correlation. In the experiment, we used DARPA data sets and launched four current practical APTs. Compared with current approaches, the results show that T-trace can efficiently reduce time cost by 90% and achieve a 92% accuracy rate in constructing the provenance graph, which can be practically applied in APTs provenance.

Keyword-based search over encrypted data is an important technique to achieve both data confidentiality and utilization in cloud outsourcing services. While commonly used access control mechanisms, such as identity-based encryption and attribute-based encryption, do not generally scale well for hierarchical access permissions. To solve this problem, we propose a Role-based Encrypted Keyword Search (REKS) scheme by using the role-based access control and broadcast encryption. Specifically, REKS allows owners to deploy hierarchical access control by allowing users with parent roles to have access permissions from child roles. Using REKS, we further facilitate token generation preprocessing and efficient user management, thereby significantly reducing the users' final token generation and index update overheads, respectively. Formal security analysis proves that REKS is secure against chosen keyword and internal keyword guessing attacks, and findings from the empirical evaluations demonstrate that REKS is efficient and practical.

Zero-knowledge scalable transparent arguments of knowledge (zk-STARKs) are a promising approach to solving the blockchain scalability problem while maintaining security, decentralization and privacy. However, compared with zero-knowledge proofs with trusted setups deployed in existing scalability solutions, zk-STARKs are usually less efficient. In this paper, we introduce Ligerolight, an optimized zk-STARK for the arithmetic circuit satisfiability problem following the framework of Ligero (ACM CCS 2017) and Aurora (Eurocrypt 2019) based on interactive oracle proof, which could be used for blockchain scalability. Evaluations show that Ligerolight has performance advantages compared with existing zk-STARKs. The prover time is 30% faster than Aurora to generate proof for computing an authentication path of a Merkle tree with 32 leaves. The proof size is about 131KB, one-tenth of Ligero and 50% smaller than Aurora. The verifier time is 2 times as fast as Aurora. Underlying Ligerolight is a new batch zero-knowledge inner product argument, allowing to prove multiple inner product relations once. Using this argument, we build a batch multivariate polynomial commitment with poly-logarithmic communication complexity and verification. This polynomial commitment is particularly efficient when opening multiple points in multiple polynomials at one time, and may be of independent interest in constructing scalability solutions.

To motivate data owner (DO) to trade data, the existing data trading allows DO to sell the disturbed data to the data consumer (DC), where the disturbance parameter and the data price are negotiated by them, and DO independently adds the disturbance noise to data (usually continuous type) following the negotiation result. However, DOs may violate the negotiated parameter and add more noise to data while obtaining the negotiated price, which damages DC's disturbed data availability. This deficiency is rooted in the absence of supervision and verifiability on DOs' independent disturbances. Aiming at the above problem, we devise a privacy-preserved data trading via verifiable data disturbance. Specifically, the honest-but-curious disturbance server (DS) is introduced to generate encrypted verifiable disturbance noises, and secretly distribute noises to DOs referring to the method of private information retrieval. Using homomorphic encryption, DOs finish data disturbance without knowing noises' specific sizes. Subsequently, DC selects DOs to verify with our proposed anti-forgery verification, where the anti-forgery on both disturbance noise and original data guarantees verification correctness. Theoretical analysis proves that DOs' original data is preserved in data trading. Extensive experiments using the real-world dataset demonstrate that our scheme can detect more than 80% of malicious DOs and decrease their utilities to punish malicious disturbance compared with existing works.

Well-trained neural network models are deployed on edge servers to provide valuable inference services for clients. To protect data privacy, a promising way is to exploit various types of secret sharing to implement privacy-preserving neural network inference. However, existing schemes suffer high communication rounds and overhead, making them hardly practical. In this paper, we propose Cenia, a new communication-efficient privacy-preserving neural network inference model. Specifically, we exploit arithmetic secret sharing to develop low-interaction secure comparison protocols, that can be used to realize secure activation layers (e.g., ReLU) and secure pooling layers (e.g., max pooling) without expensive garbled circuit and oblivious transfer primitives. Besides, we also design secure exponent and division protocols to realize secure normalization layers (e.g., Sigmoid). Theoretical analysis demonstrates the security and low complexity of Cenia. Extensive experiments have also been conducted on benchmark datasets and classical models, and experimental results show that Cenia achieves privacy-preserving, accurate, and efficient neural network inference. Particularly, Cenia can achieve 37.5% and 60.76% of Sonic’s communication rounds and overhead, respectively, compared to Sonic (i.e., the state-of-the-art scheme).

Incorporating differentially private continuous data release (DPCR) into private federated learning (FL) has recently emerged as a powerful technique for enhancing accuracy. Designing an effective DPCR model is the key to improving accuracy. Still, the state-of-the-art DPCR models hinder the potential for accuracy improvement due to insufficient privacy budget allocation and the design only for specific iteration numbers. To boost accuracy further, we develop an augmented BIT-based continuous data release (AuBCR) model, leading to demonstrable accuracy enhancements. By employing a dual-release strategy, AuBCR gains the potential to further improve accuracy, while confronting the challenge of consistent release and doubly-nested complex privacy budget allocation problem. Against this, we design an efficient optimal consistent estimation algorithm with only$O(1)$complexity per release. Subsequently, we introduce the$(k, N)$-AuBCR Model concept and design a meta-factor method. This innovation significantly reduces the optimization variables from$O(T)$to$O\left ({{lg^{2} T}}\right)$, thereby greatly enhancing the solvability of optimal privacy budget allocation and simultaneously supporting arbitrary iteration number T. Our experiments on classical datasets show that AuBCR boosts accuracy by 4.9% ~ 18.1% compared to traditional private FL and 0.4% ~ 1.2% compared to the state-of-the-art ABCRG model.

Federated Learning (FL) eliminates data silos that hinder digital transformation while training a shared global model collaboratively. However, training a global model in the context of FL has been highly susceptible to heterogeneity and privacy concerns due to discrepancies in data distribution, which may lead to potential data leakage from uploading model updates. Despite intensive research on above-identical issues, existing approaches fail to balance robustness and privacy in FL. Furthermore, limiting model updates or iterative clustering tends to fall into local optimum problems in heterogeneous (Non-IID) scenarios. In this work, to address these deficiencies, we provide lightweight privacy-preserving cross-cluster federated learning (PrivCrFL) on Non-IID data, to trade off robustness and privacy in Non-IID settings. Our PrivCrFL exploits secure one-shot hierarchical clustering with cross-cluster shifting for optimizing sub-group convergences. Furthermore, we introduce intra-cluster learning and inter-cluster learning with separate aggregation for mutual learning between each group. We perform extensive experimental evaluations on three benchmark datasets and compare our results with state-of-the-art studies. The findings indicate that PrivCrFL offers a notable performance enhancement, with improvements ranging from$0.26\%~\uparrow $to$1.35\%~\uparrow $across different Non-IID settings. PrivCrFL also demonstrates a superior communication compression ratio in secure aggregation, outperforming current state-of-the-art works by 10.59%.

Federated learning (FL) allows multiple clients to train deep learning models collaboratively while protecting sensitive local datasets. However, FL has been highly susceptible to security for federated backdoor attacks (FBA) through injecting triggers and privacy for potential data leakage from uploaded models in practical application scenarios. FBA defense strategies consider specific and limited attacker models, and a sufficient amount of noise injected can only mitigate rather than eliminate the attack. To address these deficiencies, we introduce a Robust Federated Backdoor Defense Scheme (RFBDS) and Privacy-preserving RFBDS (PrivRFBDS) to ensure the elimination of adversarial backdoors. Our RFBDS to overcome FBA consists of amplified magnitude sparsification, adaptive OPTICS clustering, and adaptive clipping. The experimental evaluation of RFBDS is conducted on three benchmark datasets and an extensive comparison is made with state-of-the-art studies. The results demonstrate the promising defense performance from RFBDS, moderately improved by 31.75% ~ 73.75% in clustering defense methods, and 0.03% ~ 56.90% for Non-IID to the utmost extent for the average FBA success rate over MNIST, FMNIST, and CIFAR10. Besides, our privacy-preserving shuffling in PrivRFBDS maintains is$7.83e^{-5}\,\,\sim \,\,0.42\times $that of state-of-the-art works.

Cloud-assisted electronic health record (EHR) sharing plays an important role in modern healthcare systems but faces threats of distrust and non-traceability. The advent of blockchain offers an attractive solution to overcome this issue. Many efforts are devoted to promoting secure, flexible, and multi-featured blockchain-based EHR sharing. Yet, the problem of seeking out suitable healthcare providers and communicating information beyond the EHR has unfortunately been ignored. In this paper, we propose SeCoSe, a novel EHR sharing scheme to address these concerns. SeCoSe enables patients and their general practitioners to autonomously seek out and stay in touch with their preferred healthcare professionals. Specifically, a searchable and repeatable transformation identity-based encryption (SRTIBE) is proposed to achieve dynamic and flexible authorization updates. Moreover, we design attribute-identity mapping contracts and evidence-based contracts on the blockchain to enable on-demand retrieval of anonymous identities and ensure tamper resistance and traceability of system transactions. Furthermore, we employ the advanced messages on-chain protocol (AMOP) to facilitate the online communication of off-chain messages. Detailed security analysis and extensive evaluations demonstrate that SeCoSe is privacy-secure, traceable, and attack-resistant. SeCoSe has lower overhead for repeated authorization and transformation, on-chain transactions can be responded to within seconds, and online communication can handle the transmission of 49,000 messages in about 6 seconds.

Federated learning not only realizes collaborative training of models, but also effectively maintains user privacy. However, with the widespread application of privacy-preserving federated learning, poisoning attacks threaten the model utility. Existing defense schemes suffer from a series of problems, including low accuracy, low robustness and reliance on strong assumptions, which limit the practicability of federated learning. To solve these problems, we propose a Robustness-enhanced privacy-preserving Federated learning with scaled dot-product attention (RFed) under dual-server model. Specifically, we design a highly robust defense mechanism that uses a dual-server model instead of traditional single-server model to significantly improve model accuracy and completely eliminate the reliance on strong assumptions. Formal security analysis proves that our scheme achieves convergence and provides privacy protection, and extensive experiments demonstrate that our scheme reduces high computational overhead while guaranteeing privacy preservation and model accuracy, and ensures that the failure rate of poisoning attacks is higher than 96%.

Boolean range query (BRQ) as a typical type of spatial keyword query that is widely used in geographic information systems, location-based services and other applications. It retrieves the objects inside the query range and containing all query keywords. Many privacy-preserving BRQ schemes have been proposed to support BRQ over encrypted data. However, most of them fail to achieve efficient retrieval and lightweight result verification while suppressing access and search pattern leakage. Thus, in this paper, we propose an efficient verifiable privacy-preserving Boolean range query with suppressed leakage. Firstly, we convert BRQ into multi-keyword query by using Gray code and Bloom filter. Then, we achieve efficient oblivious multi-keyword query by combining distributed point function and PRP-based Cuckoo hashing, which protects the access and search patterns. Moreover, we support lightweight and oblivious result verification based on oblivious query, aggregate MAC, keyed-hashing MAC and XOR-homomorphic pseudorandom function. It enables query users to verify the result integrity with a proof whose size is independent of the size of the outsourced dataset. Finally, formal security analysis and extensive experiments demonstrate that our proposed scheme is adaptively secure and efficient for practical applications, respectively.

Deep neural networks (DNNs) are vulnerable to adversarial examples, with transfer attacks in black-box scenarios posing a severe real-world threat. Adversarial perturbation is often globally manipulated image disturbances crafted in the spatial domain, leading to perceptible noise due to overfitting to the source model. Both the human visual system (HVS) and DNNs (endeavoring to mimic HVS behavior) exhibit unequal sensitivity to different frequency components of an image. In this paper, we intend to exploit this characteristic to create frequency-aware perturbation. Concentrating adversarial perturbations on components within images that contribute more significantly to model inference to enhance the performance of transfer attacks. We devise a systematic approach to select and constrain adversarial optimization in a subset of frequency components that are more critical to model prediction. Specifically, we measure the contributions of each individual frequency component and devise a scheme to concentrate adversarial optimization on these important frequency components, thereby creating frequency-aware perturbations. Our approach confines perturbations within model-agnostic critical frequency components, significantly reducing overfitting to the source model. Our approach can be seamlessly integrated with existing state-of-the-art attacks. Experiments demonstrate that while concentrating perturbation within selected frequency components yields a smaller perturbation magnitude overall, our approach does not sacrifice adversarial effectiveness. Conversely, our frequency-aware perturbation manifests superior performance, boosting imperceptibility, transferability, and evasion against various defenses.

Federated learning (FL) is an emerging paradigm for privacy-preserving machine learning, in which multiple clients collaborate to generate a global model through training individual models with local data. However, FL is vulnerable to model poisoning attacks (MPAs) as malicious clients are able to destroy the global model by modifying local models. Although numerous model poisoning defense methods are extensively studied, they remain vulnerable to newly proposed optimized MPAs and are constrained by the necessity to presume a certain proportion of malicious clients. To this end, in this paper, we propose MODEL, a model poisoning defense framework for FL through truth discovery (TD). A distinctive aspect of MODEL is its ability to effectively prevent both optimized and byzantine MPAs. Furthermore, it requires no presupposed threshold for different settings of malicious clients (e.g., less than 33% or no more than 50%). Specifically, a TD-based metric and a clustering-based filtering mechanism are proposed to evaluate local models and avoid presupposing a threshold. Furthermore, MODEL is effective for non-independent and identically distributed (non-IID) training data. In addition, inspired by game theory, we incorporate a truthful and fair incentive mechanism in MODEL to encourage active client participation while mitigating the potential desire for attacks from malicious clients. Extensively comparative experiments demonstrate that MODEL effectively safeguards against optimized MPAs and outperforms the state-of-the-art.

Outsourcing storage has emerged as an effective solution to manage the increasing volume of data. With the popularity of pay-as-you-go payment models in outsourcing storage, data auditing schemes that prioritize timeliness can be valuable evidence for elastic bill settlement. Unfortunately, existing data auditing schemes do not sufficiently consider timeliness during auditing. Furthermore, practical data auditing schemes should have the capability to check the integrity of scalable data. In this paper, we propose a blockchain-based dynamic data auditing scheme with strong timeliness to ensure that data stored in outsourcing storage systems remain intact. Our scheme encapsulates timestamps into homomorphic verifiable tags to simultaneously check data integrity and timestamp validity. To achieve dynamicity, we utilize the Merkle hash tree to store the tags, allowing for block-level dynamic operations. Additionally, by leveraging the transparency, non-repudiation, and tamper resistance of blockchain technology, we design a blockchain-based data auditing framework to prevent malicious behavior from all entities. We then formally prove the soundness and privacy of our scheme. Finally, we conduct theoretical analysis and experimental evaluation to demonstrate that the performance of our scheme is of acceptable efficiency to existing works in terms of computation cost, communication overhead, and storage overhead.

Secure outsourced computation is critical for cloud computing to safeguard data confidentiality and ensure data usability. Recently, secure outsourced computation schemes following a twin-server architecture based on partially homomorphic cryptosystems have received increasing attention. The Secure Outsourced Computation on Integers (SOCI) toolkit is the state-of-the-art among these schemes which can perform secure computation on integers without requiring the costly bootstrapping operation as in fully homomorphic encryption; however, SOCI suffers from relatively large computation and communication overhead. In this paper, we propose SOCI+ which significantly improves the performance of SOCI. Specifically, SOCI+ employs a novel (2, 2)-threshold Paillier cryptosystem with fast encryption and decryption as its cryptographic primitive, and supports a suite of efficient secure arithmetic computation on integers protocols, including a secure multiplication protocol (SMUL), a secure comparison protocol (SCMP), a secure sign bit-acquisition protocol (SSBA), and a secure division protocol (SDIV), all based on the (2, 2)-threshold Paillier cryptosystem with fast encryption and decryption. In addition, SOCI+ incorporates an offline and online computation mechanism to further optimize its performance. We perform rigorous theoretical analysis to prove the correctness and security of SOCI+. Compared with SOCI, our experimental evaluation shows that SOCI+ is up to 5.3 times more efficient in online runtime and 40% less in communication overheads.

In this paper, we propose a revocable and privacy-preserving bilateral access control scheme (named PriBAC) for general cloud data sharing (i.e., end-cloud-based data sharing). PriBAC ensures that preference matching is successful only when both parties’ preferences are satisfied simultaneously. Otherwise, nothing is leaked beyond whether the preference matching occurs. There are three challenges in designing PriBAC. The first challenge is protecting matching information, i.e., concealing two preference matching processes, in a single cloud server. The second challenge is protecting preference content while preventing receivers from receiving much useless information. The third challenge is how to integrate efficient user revocation mechanisms into bilateral access control to handle frequent user revocation cases in practical cloud data sharing applications. To address the above challenges, the punchline in PriBAC is to leverage Newton’s interpolation formula-based secret sharing to enrich the matchmaking encryption technique for constructing a privacy-preserving preference matching mechanism. To achieve efficient user revocation, we integrate a unique symbol into each user’s keys and efficiently revoke users by invaliding the corresponding keys. Security analysis proves that PriBAC can resist the chosen-ciphertext attack and preserves preference privacy and matching privacy. Experiments show that PriBAC achieves approximately$3\times $user performance improvement compared with current state-of-the-art related schemes.

Federated learning (FL) allows multiple participants to collaboratively build deep learning (DL) models without directly sharing data. Consequently, the issue of copyright protection in FL becomes important since unreliable participants may gain access to the jointly trained model. Application of homomorphic encryption (HE) in a secure FL framework prevents the central server from accessing plaintext models. Thus, it is no longer feasible to embed the watermark at the central server using existing watermarking schemes. In this article, we propose a novel client-side FL watermarking scheme to tackle the copyright protection issue in secure FL with HE. To the best of our knowledge, it is the first scheme to embed the watermark to models under a secure FL environment. We design a black-box watermarking scheme based on client-side backdooring to embed a pre-designed trigger set into an FL model by a gradient-enhanced embedding method. Additionally, we propose a trigger set construction mechanism to ensure that the watermark cannot be forged. Experimental results demonstrate that our proposed scheme delivers outstanding protection performance and robustness against various watermark removal attacks and ambiguity attack.

When enjoying mobile crowdsensing (MCS), it is vital to evaluate the trustworthiness of mobile users (MUs) without disclosing their sensitive information. However, the existing schemes ignore this requirement in the multiple crowdsourcers (CSs) scenario. The lack of a credible sharing about MUs’ trustworthiness results in an inaccurate trust evaluation, disabling allocating tasks to reliable MUs. To address it, based on the analysis of the desired properties, we propose a scheme enablingdependabledata collection withmultiple crowdsourcerstrustsharing ($D^{2}MTS$). Specifically, we design the MU anonymous management. Two kinds of MU generated pseudonym systems without relationships are presented to mark each MU in trust evaluation and task execution, respectively. Through the devised pseudonym changes on these pseudonyms and the common token distribution algorithm,$D^{2}MTS$realizes privacy-preserving trust sharing. Moreover, to guarantee credible sharing, based on the hash chain,$D^{2}MTS$records MUs’ trustworthiness with the unforgeable signature on the blockchain established by multiple CSs which do not trust each other naturally. Extensive experiments show that compared with the other works,$D^{2}MTS$'s detection ratio of vicious MUs and the percentage of reliable MUs among the selected ones can increase by 208.61% and 28.27%. Both computational and communication delays are limited.

Federated Learning (FL) suffers from low convergence and significant accuracy loss due to local biases caused by non-Independent and Identically Distributed (non-IID) data. To enhance the non-IID FL performance, a straightforward idea is to leverage the Generative Adversarial Network (GAN) to mitigate local biases using synthesized samples. Unfortunately, existing GAN-based solutions have inherent limitations, which do not support non-IID data and even compromise user privacy. To tackle the above issues, we propose a GAN-based unbiased FL scheme, calledFlGan, to mitigate local biases using synthesized samples generated by GAN while preserving user-level privacy in the FL setting. Specifically,FlGanfirst presents a federated GAN algorithm using the divide-and-conquer strategy that eliminates the problem of model collapse in non-IID settings. To guarantee user-level privacy,FlGanthen exploits Fully Homomorphic Encryption (FHE) to design the privacy-preserving GAN augmentation method for the unbiased FL. Extensive experiments show thatFlGanachieves unbiased FL with$10\%-60\%$accuracy improvement compared with two state-of-the-art FL baselines (i.e., FedAvg and FedSGD) trained under different non-IID settings. The FHE-based privacy guarantees only cost about 0.53% of the total overhead inFlGan.

There is substantial attention to federated learning with its ability to train a powerful global model collaboratively while protecting data privacy. Despite its many advantages, federated learning is vulnerable to backdoor attacks, where an adversary injects malicious weights into the global model, making the global model's targeted predictions incorrect. Existing defenses based on identifying and eliminating malicious weights ignore the similarity variation of the local weights during iterations in the malicious model detection and the presence of benign weights in the malicious model during the malicious local weight elimination, resulting in a poor defense and a degradation of global model accuracy. In this paper, we defend against backdoor attacks from the perspective of local models. First, a malicious model detection method based on interpretability techniques is proposed. The method appends a sampling check after clustering to identify malicious models accurately. We further design a malicious local weight elimination method based on local weight contributions. This method preserves the benign weights in the malicious model to maintain their contributions to the global model. Finally, we analyze the security of the proposed method in terms of model closeness and then verify the effectiveness of the proposed method through experiments. In comparison with existing defenses, the results show that BADFL improves the global model accuracy by 23.14% while reducing the attack success rate to 0.04% in the best case.

UAV-assisted mobile edge computing (UAV-MEC) has been proposed to offer computing resources for smart devices and user equipment. UAV cluster aided MEC rather than one UAV-aided MEC as edge pool is the newest edge computing architecture. Unfortunately, the data packet exchange during edge computing within the UAV cluster hasn't received enough attention. UAVs need to collaborate for the wide implementation of MEC, relying on the gossip-based broadcast protocol. However, gossip has the problem of long propagation delay, where the forwarding probability and neighbors are two factors that are difficult to balance. The existing works improve gossip from only one factor, which cannot select suitable forwarding probability and avoid redundant messages. Besides, these schemes do not consider the historical packet reception of new neighbors when UAVs fly around, which decreases forwarding efficiency. To solve these problems, we first propose a data structure called Bitgraph that can record the historical packet reception of UAVs. Then, we formulate gossip broadcasting as a partially observable Markov decision process. Based on Bitgraph, we design the reward function. Finally, we design a multi-agent reinforcement learning algorithm, Branching Deep Graph Network (BDGN), which simultaneously makes decisions on forwarding probability and neighbors. Extensive experiments illustrate that our proposal gets more than 29% advantage in terms of the propagation delay and 20% advantage in terms of the redundant messages compared to the existing works.

Privacy-preserving online multi-task assignment is a crucial aspect of spatial crowdsensing on untrusted platforms, where multiple real-time tasks are allocated to appropriate workers in a privacy-preserving manner. While existing schemes ensure the privacy of tasks and users, they seldom focus on minimizing the total moving distances for crowdsensing workers when assigning multiple tasks in real time, which adversely impacts the efficiency of online multi-task assignments. To address this issue, we propose POTA, the first privacy-preserving online multi-task assignment scheme with path planning that minimizes the total moving distances for crowdsensing workers without additional noise. POTA cryptographically implements the extended minimum-cost flow model, which models the encrypted data of workers and tasks in a graph and later produces optimized routing. With such a secure path-planning component, POTA reduces the total moving distances by$25.19\%-52.78\%$in the tested dataset compared with the state-of-the-art schemes with obfuscated path planning. Security analysis proves that POTA guarantees the confidentiality of sensitive data, a stronger security property than introducing obfuscation to sensitive data. Experimental evaluations on real-world datasets demonstrate the feasibility of POTA in terms of running time and its ability to achieve minimized total moving distances.

Assigning sensing tasks to appropriate task participants is critical for mobile crowdsensing (MCS) and is an essential optimization problem. However, existing task assignment (or say participant selection) solutions for MCS generally support a single-objective optimization (e.g., minimizing travel distance or maximizing social welfare). Additionally, task assignment for MCS usually requires task participants’ and a task requester's location information, which compromises their location privacy and hinders participation willingness. To achieve task assignment with bi-objective optimization and safeguard bilateral privacy, in this paper, we propose RATE, a privacy-preserving task assignment with bi-objective optimization for MCS. RATE features the following characteristics. First, RATE enables task assignment with bi-objective optimization including maximizing the social welfare and the requester's revenue, simultaneously. Second, RATE achieves bilateral privacy-preserving task assignment with bi-objective optimization by carefully designing underlyingly secure computing protocols. Third, RATE approximates optimal results of task assignments without sacrificing privacy. Theoretical analyses show that RATE protects the location privacy of both the task requester and the task participants. Meanwhile, experimental evaluations demonstrate that RATE outperforms traditional task assignment solutions and generates the task assignment result effectively and efficiently.

Mobile crowdsensing (MCS) has been applied in various fields to realize data sharing, where multiple platforms and multiple Mobile Users () have appeared recently. However, aiming at mutual selection, the existing works ignore making ’ utilities with the limited resources and platforms’ utilities while achieving the desired sensing data quality maximum as far as possible. Thus, they cannot motivate both and platforms to participate. To address this problem, standing on both sides of and platforms with conflicting interests, we propose a Progressive two-stage Auction-based Multi-platform Multi-user Mutual Selection scheme (). Specifically, in, we treat mutual selection as a two-stage auction and devise the auction models for and platform using forward and reverse auction ideas, presenting and maximizing the utilities from their respective perspectives. Then, based on the proposed progressive two-stage auction structure, we adopt 0-1 knapsack and Myerson’s price theory to construct the first stage -oriented auction and the second stage platform-oriented auction, achieving devised models. Theoretical analysis shows that is economically robust. Extensive experiments on the real dataset demonstrate that respectively promotes platforms’ and ’ utilities by 76.23% and 10.74 times, compared with the existing works.

The e-health system enables online healthcare by supporting health data transmission services on medical platforms. Considering the frequent privacy breaches in e-health systems and the issuance of relevant regulations, it is important to ensure the authenticity and privacy of health data. Existing e-health systems either fail to provide data authenticity or neglect privacy protection after patients leave the system. In this article, we put forward a secure and efficient e-health system for data transmission, named PPED, to solve this dilemma. In PPED, we explore a regular signature and a forward-secure signature, which guarantee data authenticity and give the signature a valid period. Then, a specific epochal signature scheme is designed by combining two signature schemes with the time-lock puzzle. Since expired epochal signatures are forgeable, patients after leaving the e-health system can forge expired signatures to deny their relationship with the signed data, thus achieving privacy protection. Detailed security analysis demonstrates the PPED realizes data authenticity and user privacy. Extensive experiments evaluate our system and the results show it is practical in terms of running time.

Users in dynamic spectrum access (DSA) with federated reinforcement learning (FRL) autonomously access channels, avoiding centralized coordination and protecting users’ privacy. However, existing FRL-based DSA mechanisms are limited to ideal network states, i.e., assuming that channel states and users’ interference relationships are unchanged. Besides, users should upload intermediate results simultaneously for federated aggregation. The above conditions are impractical for mobile users since their network states and locations are unstable. Meanwhile, newly connected users have to train their models through local data with numerous computing resources since global models are unsuitable for them. We propose FRDSA, an FRL-based secure and lightweight channel selection mechanism in DSA for mobile users under dynamic network states. An independent channel selection environment with a virtual group strategy is presented to avoid interference between users under unstable channel states. Furthermore, an asynchronous parameter aggregation method in FRDSA dynamically adjusts the aggregation factors without users simultaneously uploading intermediate results. Simulations based on real trajectory data show that FRDSA significantly reduces approximately 60% interference between mobile users under unstable network states. Newly connected users can directly apply the well-trained global model to access channels autonomously instead of retraining a model, effectively reducing mobile users’ computing resource requirements.

As acquiring manual labels on data could be costly, unsupervised domain adaptation (UDA), which transfers knowledge learned from a rich-label dataset to the unlabeled target dataset, is gaining increasingly more popularity. While extensive studies have been devoted to improving the model accuracy on target domain, an important issue of model robustness is neglected. To make things worse, conventional adversarial training (AT) methods for improving model robustness are inapplicable under UDA scenario since they train models on adversarial examples that are generated by supervised loss function. In this paper, we present a new meta self-training pipeline, named SRoUDA, for improving adversarial robustness of UDA models. Based on self-training paradigm, SRoUDA starts with pre-training a source model by applying UDA baseline on source labeled data and taraget unlabeled data with a developed random masked augmentation (RMA), and then alternates between adversarial target model training on pseudo-labeled target data and fine-tuning source model by a meta step. While self-training allows the direct incorporation of AT in UDA, the meta step in SRoUDA further helps in mitigating error propagation from noisy pseudo labels. Extensive experiments on various benchmark datasets demonstrate the state-of-the-art performance of SRoUDA where it achieves significant model robustness improvement without harming clean accuracy.

Transferability of adversarial examples is of critical importance to launch black-box adversarial attacks, where attackers are only allowed to access the output of the target model. However, under such a challenging but practical setting, the crafted adversarial examples are always prone to overfitting to the proxy model employed, presenting poor transferability. In this paper, we suggest alleviating the overfitting issue from a novel perspective, i.e., designing a fitted model architecture. Specifically, delving the bottom of the cause of poor transferability, we arguably decompose and reconstruct the existing model architecture into an effective model architecture, namely multi-track model architecture (MMA). The adversarial examples crafted on the MMA can maximumly relieve the effect of model-specified features to it and toward the vulnerable directions adopted by diverse architectures. Extensive experimental evaluation demonstrates that the transferability of adversarial examples based on the MMA significantly surpass other state-of-the-art model architectures by up to 40% with comparable overhead.

While the transferability property of adversarial examples allows the adversary to perform black-box attacks (i.e., the attacker has no knowledge about the target model), the transfer-based adversarial attacks have gained great attention. Previous works mostly study gradient variation or image transformations to amplify the distortion on critical parts of inputs. These methods can work on transferring across models with limited differences, i.e., from CNNs to CNNs, but always fail in transferring across models with wide differences, such as from CNNs to ViTs. Alternatively, model ensemble adversarial attacks are proposed to fuse outputs from surrogate models with diverse architectures to get an ensemble loss, making the generated adversarial example more likely to transfer to other models as it can fool multiple models concurrently. However, existing ensemble attacks simply fuse the outputs of the surrogate models evenly, thus are not efficacious to capture and amplify the intrinsic transfer information of adversarial examples. In this paper, we propose an adaptive ensemble attack, dubbed AdaEA, to adaptively control the fusion of the outputs from each model, via monitoring the discrepancy ratio of their contributions towards the adversarial objective. Furthermore, an extra disparity-reduced filter is introduced to further synchronize the update direction. As a result, we achieve considerable improvement over the existing ensemble attacks on various datasets, and the proposed AdaEA can also boost existing transfer-based attacks, which further demonstrates its efficacy and versatility. The source code: https://github.com/CHENBIN99/AdaEA

Spatial range query enjoys widespread application scenarios due to the ever-growing geo-positioning technology in recent years. Huge amounts of encrypted geo-location data are being outsourced to cloud servers to alleviate local storage and computational overheads without leaking sensitive information. However, most existing Privacy-preserving Spatial Range Query (PSRQ) cannot achieve high efficiency while satisfying strong security over large-scale encrypted spatial data. To strike a best possible balance between security and efficiency, we propose a novel efficient Privacy-preserving Spatial Range Query (eP-SRQ) scheme in dual-cloud architecture over large-scale dataset. Specifically, we propose an efficient PSRQ scheme by designing a novel index structure based on Geohash algorithm, Circular Shift and Coalesce Zero-Sum Garbled Bloom Filter (CSC-ZGBF) and Symmetric Homomorphic Encryption (SHE), which makes the computational complexity of query process independent of dataset size. Formal security analysis proves that our scheme can achieve Indistinguishability against Chosen-Plaintext Attack (IND-CPA), and extensive experiments prove that our scheme is feasible in real-world applications.

To obtain reliable results from conflicting data in mobile crowdsensing, numerous truth discovery protocols have been proposed in the past decade. However, most of them do not consider the data privacy of entities involved (e.g., workers and servers), and several existing privacy-preserving truth discovery protocols either provide limited privacy protection or have heavy computation and communication overheads due to iterative computation and transmission over large ciphertexts.In this paper, we aim to propose privacy-preserving and lightweight truth discovery protocols to tackle the above problems. Specifically, we carefully design an anonymization protocol named AnonymTD to delink workers from their data, where workers’ data are computed and transmitted without complicated encryption. To further reduce each worker’s overheads in the scenarios where workers are willing to share their weights, we resort to the perturbation technology to propose a more lightweight truth discovery protocol named PerturbTD. Based on workers’ perturbed data, two cloud servers in PerturbTD complete most of the workload of truth discovery together, which avoids the frequent involvement of workers. The theoretical analysis and the comparative experiments in this paper demonstrate that our two protocols can achieve our security goals with low computation and communication overheads.

Federated learning (FL) enables multiple clients to collaboratively train deep learning models while considering sensitive local datasets’ privacy. However, adversaries can manipulate datasets and upload models by injecting triggers for federated backdoor attacks (FBA). Existing defense strategies against FBA consider specific and limited attacker models, and a sufficient amount of noise to be injected only mitigates rather than eliminates FBA. To address these deficiencies, we introduce a Flexible Federated Backdoor Defense Framework (Fedward) to ensure the elimination of adversarial backdoors. We decompose FBA into various attacks, and design amplified magnitude sparsification (AmGrad) and adaptive OPTICS clustering (AutoOPTICS) to address each attack. Meanwhile, Fedward uses the adaptive clipping method by regarding the number of samples in the benign group as constraints on the boundary. This ensures that Fedward can maintain the performance for the Non-IID scenario. We conduct experimental evaluations over three benchmark datasets and thoroughly compare them to state-of-the-art studies. The results demonstrate the promising defense performance from Fedward, moderately improved by 33% ∼ 75% in clustering defense methods, and 96.98%, 90.74%, and 89.8% for Non-IID to the utmost extent for the average FBA success rate over MNIST, FMNIST, and CIFAR10, respectively.

Graph neural networks (GNNs) have been applied successfully in many machine learning tasks due to their advantages in utilizing neighboring information. Recently, with the global enactment of privacy protection regulations, federated GNNs have gained increasing attention in academia and industry. However, the graphs owned by different participants could be non-independently-and-identically distributed (non-IID), leading to the deterioration of federated GNNs' accuracy. In this paper, we propose a globally consistent federated graph autoencoder (GCFGAE) to overcome the non-IID problem in unsupervised federated graph learning via three innovations. First, by integrating federated learning with split learning, we train a unique global model instead of FedAvg-styled global and local models, yielding results consistent with that of the centralized GAE. Second, we design a collaborative computation mechanism considering overlapping vertices to reduce communication overhead during forward propagation. Third, we develop a layer-wise and block-wise gradient computation strategy to reduce the space and communication complexity during backward propagation. Experiments on real-world datasets demonstrate that GCFGAE achieves not only higher accuracy but also around 500 times lower communication overhead and 1000 times smaller space overhead than existing federated GNN models.

The social trust assessment can spur extensive applications such as social recommendations, shopping, financial investment strategies, etc, but remain a challenging problem having limited exploration. Such explorations mainly limit their studies to static network topology or simplified dynamic networks, toward the social trust relationship prediction. In contrast, in this paper, we explore the social trust by taking into account the time-varying online social networks whereas the social trust relationship may vary over time. The DTrust, a dynamic graph neural network-based solution, will be proposed for accurate social trust prediction. In particular, DTrust is composed of a static aggregation unit and a dynamic unit, respectively responsible for capturing both the spatial dependence features and temporal dependence features. In the former unit, we stack multiple NNConv layers derived from the edge-conditioned convolution network for capturing the spatial dependence features correlated to the network topology and the observed social relationships. In the latter unit, a gated recurrent unit (GRU) is employed for learning the evolution law of social interaction and social trust relationships. Based on the extracted spatial and temporal features, we then employ a fully connected neural network for learning, able to predict the social trust relationships for both current and future time slots. Extensive experimental results exhibit that our DTrust can outperform the benchmark counterparts on two real-world datasets.

Abstract As the scale of the system expands, processor failures are inevitable. Fault diagnosis has great significance in analyzing the reliability of multiprocessing systems. Probabilistic fault diagnosis is a method that attempts to diagnose nodes correctly with high probability. In this paper, we extend the threshold $t \leq 2$ to threshold $t=3$ for regular networks based on probabilistic diagnosis algorithm and determine the status of a cluster of nodes by analyzing the local performance. Moreover, we evaluate the global performance based on the Poisson distribution and the Binomial distribution and show that the achievement in terms of correctness demonstrates a good performance. Finally, we employ the probabilistic diagnosis scheme to explore some well-known networks, including complete cubic networks, dual cubes and hierarchical hypercubes as well.

Abstract Fine‐grained access control become a research spotlight in the scenario of the smart home with Internet‐of‐Things (IoTs). However, most of the existing works could only realize ciphertext outsourcing with an unchangeable encryption key in the cloud. That is because the trivial solution needs great communication overhead. To overcome this challenge, we propose an updatable encryption based on SM9 (SM9‐UE) scheme for the IoT smart home scenario, where SM9 is an identity and cryptographic standard adopted by GM/T0044. SM9‐UE realizes secure and lightweight ciphertext updating through using the token generated by the data owner, which is information independent with the plaintext. We give the formal security definition and prove it to be adaptive update indistinguishability (IND‐UPD) secure. Theoretical comparison and analysis show that our scheme is efficient in computation and storage overhead. Experimental results also indicate that SM9‐UE can be practically applied to IoT smart home.

With the prosperous development of Internet of Things (IoT), IoT devices have been deployed in various applications, which generates large volume of image data to trace and record the users’ behaviors, resulting in better IoT services. To accurately analyze these huge data to further improve users’ experience on IoT services, deep neural networks (DNNs) are gaining more attention and have become increasingly popular. However, recent studies have shown that DNN models are vulnerable to adversarial attacks, which leads to the risk of applications in practice. Previous works are devoted to extract invariant features from the content circled by edges in images, while such features cannot efficiently deal with the adversarial effect. In this work, we first study this problem from a new angle by exploring the edge feature information, which is intractable to be influenced by adversarial attacks demonstrated by our empirical analysis. Based on this, we propose a novel edge feature-enhanced defense approach called Defed which incorporates edge feature information into denoised network to defend against various adversarial attacks in image area. For the training phase, we only add benign images as the input and exert Gaussian noise to substitute the adversarial attacks to mitigate the dependency of models on specific adversarial attacks. For inference, we design a combination of multiple Defeds trained by different Gaussian noise levels and deploy confidence intervals to judge whether an image is adversarial or not. Experiments over real-world data sets on image classification demonstrate the efficacy and superiority compared to the state-of-the-art defense approaches.

In unmanned aerial vehicle (UAV) performing tasks, the UAV often faces electricity shortages. The traditional scheme to charge a UAV needs to return to the ground. Using the charging UAV (CUAV) can avoid the waste of electricity caused by the return. However, the existing works only consider a fixed charging location for electricity replenishment. Moreover, fewer works focus on the matching relationship between multi-CUAV and multi-UAV. It is challenging to complete the expected charging work due to the mismatch between the electricity demand and supply. To address this problem, we propose a two-stage electricity scheduling scheme. Specifically, in the charging location selection stage, we solve the Nash equilibrium (NE) of flight consumption between CUAVs and UAVs through the exact potential game, thereby determining the accessible charging position. Then, in the electricity transaction stage, we adopt the Stackelberg game model to determine the Stackelberg equilibrium (SE) between the acceptance rate of CUAVs and the rejection rate of UAVs, ensuring that both CUAVs and UAVs are satisfied with the unit electricity prices and electricity demands. Based on the above two game stages, we propose a supply and demand scheduling (SDS) algorithm to achieve dynamic scheduling between CUAVs and UAVs. Theoretical analysis indicates the exits of NE and SE. Furthermore, the extensive experiments show that our scheme has significant advantages over the baselines in charging cost, charging price, and flight consumption.

Smart logistics (s-Logistics) has become more and more popular driven by the intelligent Internet of Things (IoT) which deploys pervasive smart devices in s-Logistics systems. The explosive growth of s-Logistics data collected by these resource-limited IoT devices enables Fog-based s-Logistics that provides data outsourcing and sharing services via multiple clouds within small latency. Nevertheless, it also gives rise to prominent security risks of user privacy leakage considering malicious users and data integrity violation with untrusted cloud servers, which are severe to s-Logistics systems and cannot be addressed by simple encryption. To solve these issues, in this article, we propose an efficient large universe and traceable privacy-preserving data sharing (LUTPDS) for Fog-based s-Logistics. It simultaneously achieves data access control, data integrity protection, key escrow and abuse resistance, user privacy preserving, and scalability. We devise a large universe and multiauthority ciphertext-policy attribute-based encryption (CP-ABE) scheme in which access policy hiding mechanism is used for user privacy preserving, while white-box tracing and certificateless public data integrity auditing techniques are employed to resist key abuse and escrow problems. In addition, online/offline encryption and verifiable outsourced decryption are leveraged for high efficiency and cloud encryption is utilized to extend to multiple clouds. In the end, we formally prove the security of our scheme for indistinguishability of chosen plaintext attack (IND-CPA) security and traceability. Detailed performance evaluation with extensive experiments shows that our scheme is practicable for s-Logistics compared with the existing schemes.

Federated learning is a popular framework designed to perform the distributed machine learning while protecting client privacy. However, the heterogeneous data distribution in real-world environments makes it difficult to converge when performing model training. In this article, we propose the federated gradient scheduling (FedGS), an improved historical gradient sampling utilization method for optimizers that utilize historical gradients in the federated learning to alleviate the instability problem of historical gradient information due to non-IID. FedGS consists of two main steps to improve federated learning performance. First, clustering uses clients’ label distributions, which relabel clients and their submitting gradients. Second, sampling gradient clusters to generate an IID gradient set, which feeds to optimizers to derive valid momentum information. Besides, we introduce differential privacy to collaborate with FedGS to enhance clients’ privacy protection strength. Compared to previous non-IID federated learning solutions, our method can achieve greater resistance to temporal non-IID. Moreover, experiments show that FedGS can achieve faster convergence and performance gain of up to 10% over existing state-to-art methods in some scenarios. FedGS can combine with existing methods easily to achieve better performance. We further verify that our method has robust performance gains in different non-IID scenarios, demonstrating the adaptability of FedGS for different scenarios.

Centralized learning now faces data mapping and security constraints that make it difficult to carry out. Federated learning with a distributed learning architecture has changed this situation. By restricting the training process to participants’ local, federated learning addresses the model training needs of multiple data sources while better protecting data privacy. However, in real-world application scenarios, federated learning faces the need to achieve fairness in addition to privacy protection. In practice, it could happen that some federated learning participants with specific motives may short join the training process to obtain the current global model with only limited contribution to the federated learning whole, resulting in unfairness to the participants who previously participated in federated learning. We propose the FedACC framework with a server-initiated global model accuracy control method to address this issue. Besides measuring the accumulative contributions of newly joined participants and providing participants with a model with an accuracy that matches their contributions, the FedACC still guarantees the validity of participant gradients based on the accuracy-decayed model. Under the FedACC framework, users do not have access to the full version of the current global model early in their training participation. However, they must produce a certain amount of contributions before seeing the full-accuracy model. We introduce an additional differential privacy mechanism to protect clients’ privacy further. Experiments demonstrate that the FedACC could obtain about 10%–20% accuracy gain compared to the state-of-the-art methods while balancing the fairness, performance, and security of federated learning.

Abstract Deep learning techniques have been widely used in natural language processing (NLP) tasks and have made remarkable progress. However, training the deep learning model relies on a large amount of data which may involve sensitive information like electronic medical records. The attacker can infer sensitive information from the model, which leads to privacy leakage. To solve this problem, we propose a Differentially Private Recurrent Variational AutoEncoder (DP-RVAE) that can generate simulated data in place of the sensitive dataset to preserve privacy. To generate high utility synthetic text, a part of sensitive text data is employed as the conditional input of the model and uses a dropout and noise perturbing mechanism to preserve differential privacy. In addition, we expand the proposed DP-RVAE to a federated learning setting and design a novel training paradigm for NLP tasks. Specifically, DP-RVAE is deployed to the client-side to train and generate personalized text. These DP-RVAE models would be aggregated and updated through the Federated Optimisation (FedOPT) algorithm so that personal information can be well preserved. We evaluate our proposed DP-RVAE through a text classification task on the Tweets depression sentiment and IMDB reviews datasets. Our DP-RVAE achieves a higher average test accuracy by 5.90% and 3.94% compared to the typical centralized training and federated learning approach, respectively. We also perform the keywords inference attack experiment on the medical description dataset collected from the real world. Compared to the typical differentially private preserving approach, the DP-RVAE decreases by 15.2% in average attack accuracy. The experimental results demonstrate that DP-RVAE can be applied to the NLP models to leverage accuracy while preserving sensitive privacy.

The advances in deep neural networks (DNNs) have driven many companies to offer their carefully-trained DNNs as inference services for clients’ private data. The privacy concerns have increasingly motivated the need for private inference (PI), where DNN inferences are performed directly on encrypted data without revealing the client's private inputs to the server or revealing the server's proprietary DNN weights to the client. However, existing cryptographic protocols for PI suffer from impractically high latency, stemming mostly from non-linear operators like ReLU activations. In this paper, we propose PAPI, a Practical and Adaptive Private Inference framework. First, we develop an accuracy-adaptive neural architecture search (NAS) approach to generate DNN models tailored for high-efficiency ciphertext computation. Specifically, our NAS automatically generates the DNNs with fewer ReLUs while keeping the accuracy above a user-defined target. Second, we propose secure online/offline protocols for ReLU activation and its approximation variants (i.e., polynomial activations), which purely rely on the lightweight secret sharing techniques in the online execution and can well cope with our optimized DNNs in the ciphertext domain. Experimental results show that PAPI reduces online inference latency on the CIFAR-10/100 and ImageNet datasets by 2.7${\times}$$\sim$7.8${\times}$over the state-of-the-art.

In various multi-party cooperations data stored on blockchains (i.e., on-chain data) should be decentralized consistent, verifiable, traceable, and immutable. Online analytical processing (OLAP) services are critical requirements in these applications. However, OLAP performances of existing blockchain systems are much worse than those of relational databases due to the lack of SQL support. In this paper, we propose a novel SQL-empowered analytical blockchain framework, aChain. It fully provides SQL-based OLAP services, while keeping the secure characteristics. Specifically, aChain relationally reorganizes on-chain data to support full SQL executions. Then, a relational versioning scheme is designed to ensure the atomicity and consistency of transactions. Furthermore, SQL-based APIs are designed based on an execute-order-validate architecture. Finally, we demonstrate that the performance of aChain and MySQL (in both cluster and non-cluster models) is at the same level on a typical OLAP benchmark, TPC-H.

The$k$-ary$n$-cube$Q_{n}^{k}$is one of the most popular interconnection networks engaged as the underlying topology of data center networks, on-chip networks, and parallel and distributed systems. Due to the increasing probability of faulty edges in large-scale networks and extensive applications of the Hamiltonian path, it becomes more and more critical to investigate the fault tolerability of interconnection networks when embedding the Hamiltonian path. However, since the existing edge fault models in the current literature only focus on the entire status of faulty edges while ignoring the important information in the edge dimensions, their fault tolerability is narrowed to a minimal scope. This article first proposes the concept of the partitioned fault model to achieve an exponential scale of fault tolerance. Based on this model, we put forward two novel indicators for the bipartite networks (including$Q^{k}_{n}$with even$k$), named partition-edge fault-tolerant Hamiltonian laceability and partition-edge fault-tolerant hyper-Hamiltonian laceability. Then, we exploit these metrics to explore the existence of Hamiltonian paths and unpaired 2-disjoint path cover in$k$-ary$n$-cubes with large-scale faulty edges. Moreover, we prove that all these results are optimal in the sense that the number of edge faults tolerated has attended to the best upper bound. Our approach is the first time that can still embed a Hamiltonian path and an unpaired 2-disjoint path cover into the$k$-ary$n$-cube even if the faulty edges grow exponentially.

With the rapid development of cloud computing and Internet of Things (IoT), smart health (s-health) is anticipated to enhance healthcare quality significantly. However, data integrity, user anonymity, and authentication concerns have not been adequately addressed in s-health. Remote data integrity checking (RDIC) and digital signature schemes have great potential to address these requirements. Nevertheless, the direct adoption of these schemes suffers from two flaws. Firstly, they incur prohibitively high computation and communication overhead. Secondly, they leak sensitive health information about patients and do not provide complete anonymity. To address these issues, we introduce$\mathbf {A^{3}B}$-$\mathbf {RDV}$, an aggregate anonymous attribute-based remote data verification scheme. In$\mathbf {A^{3}B}$-$\mathbf {RDV}$, the integrity of an arbitrary number of cloud data files can be verified at once without downloading the whole data, thereby saving communication and computation resources. Moreover, in$\mathbf {A^{3}B}$-$\mathbf {RDV}$, data owners can be authenticated by performing highly efficient operations. Also,$\mathbf {A^{3}B}$-$\mathbf {RDV}$provides complete anonymity and supports dishonest-user traceability. We provide security definitions for$\mathbf {A^{3}B}$-$\mathbf {RDV}$and prove its security under the hardness assumption of the bilinear Diffie-Hellman (BDH) problem. Performance comparisons and experimental results indicate that$\mathbf {A^{3}B}$-$\mathbf {RDV}$is more efficient and expressive than state-of-the-art approaches.

Searchable Symmetric Encryption (SSE), which enables users to search over encrypted data without decryption, has gained increasing attention from both academic and industrial fields. However, existing SSE schemes either have low search efficiency or cannot support multi-keyword search, dynamic updates, and result verification simultaneously. To solve these problems, we propose a Verifiable and Dynamic Multi-keyword Search (VDMS) scheme over encrypted data by using the bitmap and RSA accumulator, which provides multi-keyword search over encrypted data in an efficient, verifiable and updated way. The bitmap is used as a data structure to build the indexes, which improves the search efficiency and reduces the storage space of the indexes. The RSA accumulator and bitmap are combined to verify the correctness of results. Formal security analysis proves that our VDMS is adaptively secure against Chosen-Keyword Attacks (CKA), and empirical experiments using a real-world dataset demonstrate that our VDMS is efficient and feasible in practical applications.

Symmetric Searchable Encryption (SSE) schemes facilitate searching over encrypted data, and have been extensively explored to improve function, efficiency or security. There are, however, additional functions that we need to consider in a real-world setting. For example, forward and backward privacy are required to adequately secure newly added documents and deleted documents in Dynamic SSE (DSSE) schemes, and support boolean search (that allows users to search over encrypted data using basic boolean operations) to achieve improved efficiency and retrieval accuracy. Therefore, in this article we first construct the Verifiable Boolean Search over encrypted data (VBS), and then improve VBS to achieve Forward and Backward privacy (VBS-FB). Finally, we formally prove the security of our proposed schemes, and evaluate their performance using real-world datasets.

The traveling salesman problem (TSP) is one of the classic combinatorial optimization problems, which can be widely used in intelligent transportation and logistics field. Neural network has shown great potential in combinatorial optimization tasks. However, it faces privacy leakage when a TSP neural combinatorial optimization network and user's data are directly outsourced to a cloud platform to provide and request service. In order to address the issue, this article proposes a privacy-preserving service framework for a TSP-based neural combinatorial optimization network called PPSF. We first protect the service provider's model parameters and users’ data by different split methods in multiple cloud servers, providing a secure outsourced mode for the participators in the PPSF framework. Then, in the secure outsourced mode, a series of secure computation protocols are designed for the cloud servers to support performing the secure computing in each service task. Moreover, it can also protect the process that the cloud servers respond to users after data processing and achieve private service result recovery. Finally, we prove that the proposed framework can realize privacy protection for TSP-based combinatorial optimization service and verify its utility and efficiency by experiments.

Efficiently mining frequent itemsets and association rules on the encrypted outsourced data remains a great challenge for the time-consuming ciphertext computations. Nowadays, it has been not well addressed for privacy-preserving frequent itemsets and association rule mining schemes with mining efficiency, dataset, and query confidentiality simultaneously. In this paper, we investigate the study of privacy issues on frequent itemset mining and association rule mining on outsourced data in a two-cloud model, where the data are encrypted and outsourced by multiple owners holding different public keys. We develop several secure computation protocols based on additively homomorphic cryptosystem and additive secret sharing, which enable the clouds could securely mine the frequent itemsets and association rules. Furthermore, we also design two kinds of frequent itemset and association rule query service models, i.e., service customers query the cloud-mined results, and service customers query with their own decided threshold. The proposed scheme not only supports the mining process on the data encrypted by multiple public keys without compromising the security of the datasets, query data and query results, but also offline users. In addition, the experimental results show that our query scheme is much more efficient than the state-of-the-art work.

With the advent of Cloud-storages, secure sharing of encrypted data with fine-grained access control has become an important challenge. To enforce fine-grained access rights on encrypted data to different users, Attribute-Base Encryption (ABE) is a promising cryptographic tool. But in many situations, some pirate users sell their access privileges for monetary gain. Hence, an efficient Black-Box Traitor Tracing (BB-TT) system is vital to address the corresponding Pirate Decoders (PDs). But, in the existing BB-TTs, the tracing complexity is directly related to the maximum number of users in the system. This paper proposes an ABE-based access control system that provides a new Relaxed BB-TT. Our Relaxed BB-TT addresses the complexity problem by exploring the pirate user with an optimal number of decryption queries on the PD. The optimal number of queries leads to the exciting capability of traceability of stateful decoders (i.e., the decoder that can save the states among theTracer's queries). Finally, our system provides White-Box traceability and reduces the amount of trust in the authorities. We give formal security proofs and extensive experimental results on different classes of mobile devices, including a laptop and a smartphone.

Recommendation systems have been widely developed and extensively used in various websites and platforms to promote products or services to interested users. However, in quite a few sale scenarios, the platform has the necessity to display users a series of items, which is called package recommendation. There is very little research in this area. This article develops a novel and realistic package recommendation system named package graph attention network (PGAT) based on graph neural network. PGAT integrates users, items, and packages to build a unified heterogeneous graph and treat them as a whole. PGAT incorporates an attention mechanism in the first-order neighborhood aggregation operation, which can differentiate the weight of different neighbor nodes to the center node. By performing graph attention and graph convolution operations on the tripartite graph, PGAT can learn node embeddings more expressively and address the problem of data sparse to a large extent. Extensive experiment results on two real-world datasets validate the outstanding performance of PGAT, which is superior to the state-of-the-art baselines by 0.77%–10.12%.

Centralized particle swarm optimization (PSO) does not fully exploit the potential of distributed or parallel computing and suffers from single-point-of-failure. Particularly, each particle in PSO comprises a potential solution (e.g., traveling route and neural network model parameters) which is essentially viewed as private data. Unfortunately, previously neither centralized nor distributed PSO algorithms fail to protect privacy effectively. Inspired by secure multiparty computation and multiagent system, this article proposes a privacy-preserving multiagent PSO algorithm (called PriMPSO) to protect each particle's data and enable private data sharing in a privacy-preserving manner. The goal of PriMPSO is to protect each particle's data in a distributed computing paradigm via existing PSO algorithms with competitive performance. Specifically, each particle is executed by an independent agent with its own data, and all agents jointly perform global optimization without sacrificing any particle's data. Thorough investigations show that selecting an exemplar from all particles and updating particles through the exemplar are critical operations for PSO algorithms. To this end, this article designs a privacy-preserving exemplar selection algorithm and a privacy-preserving triple computation protocol to select exemplars and update particles, respectively. Strict privacy analyses and extensive experiments on a benchmark and a realistic task confirm that PriMPSO not only protects particles' privacy but also has uniform convergence performance with the existing PSO algorithm in approximating an optimal solution.

As embedded integrated electronic systems (EIESs) become more pervasive (including in mission-critical applications), the need to ensure the security of data exchange in such a system against various malicious activities becomes more pronounced. However, designing secure and efficient solutions, such as authentication protocols, for the many different embedded systems with varying internal communication modes remains challenging. Therefore, in this paper, we propose a lightweight authenticated key-exchange (AKE) protocol for EIESs based on half-duplex and “command/response” bus. Specifically, the proposed protocol is designed to operate on resource-constrained devices, as well as having minimal number of interactions. We then prove the security of the proposed protocol and present the security parameter selection strategy for protocol implementation based on the empirical evaluations. Moreover, efficiency analysis also shows that the protocol can be effectively deployed in the EIESs environment.

As one of the most popular relational databases for embedded devices, SQLite is lightweight to be embedded into applications without installing a specific database management system. However, simplicity and easy-to-use are double-edged swords; while bringing convenience, they also make data processing and storage risky. For example, an attacker can obtain data from a database file or memory and tamper with it once he has gained higher privileges, threatening the database's confidentiality and integrity. To address such security issues, based on a trusted execution environment (TEE) and a trusted platform module (TPM), we have proposed Smaug, a general secure scheme to ensure the confidentiality and integrity of SQLite and similar databases. With Smaug, all the critical data is stored in ciphertext, and data integrity protection is also provided. Besides, with TEE, all the sensitive operations are isolated from the untrusted environment, which can effectively resist attacks against memory. In addition, we use TPM to provide a solid root-of-trust (RoT) for the system. Finally, we have implemented a prototype system, and the performance evaluations have clarified the dominant factors that affect the system availability, providing a reference to the design and implementation of similar systems.

Organizations tend to collaboratively train the deep learning model over their combined datasets for a common benefit (e.g., better-trained model or learning a complicated model). However, due to the consideration about privacy leakage, organizations cannot share their data directly, especially related to sensitive domains. In this paper, a privacy-preserving collaborative deep learning mechanism, namely Sigma, is designed to allow participating organizations to train a collective model without exposing their local training data to the others. Specifically, a single-server-aided private collaborative architecture is introduced to achieve the private collaborative learning, which protects organizations’ data even if$n-1$out of$n$participants colluded. We also design a practical protocol to perform the secure model training, which can resist the typical inference attack through the sharing information. After that, we propose a fair model releasing mechanism for participants and introduce differential privacy to prevent model stealing and membership inference attack. Furthermore, we prove that Sigma can ensure participants’ privacy preservation and analyze the communication overhead in theory. To evaluate the effectiveness and efficiency of Sigma, we conduct an experiment over two real-world datasets and the simulation results demonstrate that Sigma can efficiently achieve the collaborative model training and effectively resist the membership inference attack.

Nowadays, machine learning models, especially neural networks, have became prevalent in many real-world applications. These models are trained based on a one-way trip from user data: as long as users contribute their data, there is no way to withdraw. To this end,machine unlearningbecomes a popular research topic, which allows the model trainer to unlearn unexpected data from a trained machine learning model. In this article, we propose the first uniform metric called forgetting rate to measure the effectiveness of a machine unlearning method. It is based on the concept of membership inference and describes the transformation rate of the eliminated data from “memorized” to “unknown” after conducting unlearning. We also propose a novel unlearning method calledForsaken. It is superior to previous work in either utility or efficiency (when achieving the same forgetting rate). We benchmarkForsakenwith eight standard datasets to evaluate its performance. The experimental results show that it can achieve more than 90% forgetting rate on average and only causeless than 5% accuracy loss.

Recently, model stealing attacks are widely studied but most of them are focused on stealing a single non-discrete model, e.g., neural networks. For ensemble models, these attacks are either non-executable or suffer from intolerant performance degradation due to the complex model structure (multiple sub-models) and the discreteness possessed by the sub-model (e.g., decision trees). To overcome the bottleneck, this paper proposes a divide-and-conquer strategy called DivTheft to formulate the model stealing attack to common ensemble models by combining active learning (AL). Specifically, based on the boosting learning concept, we divide a hard ensemble model stealing task into multiple simpler ones about single sub-model stealing. Then, we adopt AL to conquer the data-free sub-model stealing task. During the process, the current AL algorithm easily causes the stolen model to be biased because of ignoring the past useful memories. Thus, DivTheft involves a newly designed uncertainty sampling scheme to filter reusable samples from the previously used ones. Experiments show that compared with the prior work, DivTheft can save almost 50% queries while ensuring a competitive agreement rate to the victim model.

Getting access to labeled datasets in certain sensitive application domains can be challenging. Hence, one may resort to transfer learning to transfer knowledge learned from a source domain with sufficient labeled data to a target domain with limited labeled data. However, most existing transfer learning techniques only focus on one-way transfer which may not benefit the source domain. In addition, there is the risk of a malicious adversary corrupting a number of domains, which can consequently result in inaccurate prediction or privacy leakage. In this paper, we construct a secure andVerifiable collaborativeTransferLearning scheme, VerifyTL, to support two-way transfer learning over potentially untrusted datasets by improving knowledge transfer from a target domain to a source domain. Furthermore, we equip VerifyTL with a secure and verifiable transfer unit employing SPDZ computation to provide privacy guarantee and verification in the multi-domain setting. Thus, VerifyTL is secure against malicious adversary that can compromise up to$n-1$out of$n$data domains. We analyze the security of VerifyTL and evaluate its performance over four real-world datasets. Experimental results show that VerifyTL achieves significant performance gains over existing secure learning schemes.

Spatial keyword queries are attractive techniques that have been widely deployed in real-life applications in recent years, such as social networks and location-based services. However, existing solutions neither support dynamic update nor satisfy the privacy requirements in real applications. In this article, we investigate the problem of Dynamic Searchable Symmetric Encryption (DSSE) for spatial keyword queries. First, we formulate the definition of DSSE for spatial keyword queries (namely, DSSESKQ) and extend the DSSE leakage functions to capture the leakages in DSSESKQ. Then, we present a practical DSSESKQ construction based on geometric prefix encoding inverted-index and encrypted bitmap. Rigorous security analysis proves that our construction can achieve not only forward/backward privacy but content privacy as well, which can resist the most existing leakage-abuse attacks. Evaluation results using real-world datasets demonstrate the efficiency and feasibility of our construction. Comparative analysis reveals that our construction outperforms state-of-the-art schemes in terms of privacy and performance, e.g., our construction is 175x faster than existing schemes with only 51% server storage cost.

The neural network has been widely used to train predictive models for applications such as image processing, disease prediction, and face recognition. To produce more accurate models, powerful third parties (e.g., clouds) are usually employed to collect data from a large number of users, which however may raise concerns about user privacy. In this paper, we propose an Efficient and Privacy-preserving Neural Network scheme, named EPNN, to deal with the privacy issues in cloud-based neural networks. EPNN is designed based on a two-cloud model and techniques of data perturbation and additively homomorphic cryptosystem. This scheme enables two clouds to cooperatively perform neural network training and prediction in a privacy-preserving manner and significantly reduces the computation and communication overhead among participating entities. Through a detailed analysis, we demonstrate the security of EPNN. Extensive experiments based on real-world datasets show EPNN is more efficient than existing schemes in terms of computational costs and communication overhead.

The surging interest in cryptocurrency has revitalized the research for digital signature schemes with strong security. In particular, signature schemes are investigated to resist the malleability attacks in cryptocurrency platforms. However, existing signature schemes only conquer partial malleability attacks due to various sources of attacks. Other solutions of new transaction realizations cannot simultaneously avoid the malleability attacks on both standard and contract transactions. Furthermore, the malleability attack becomes more stubborn in fast clearing applications. In this paper, we propose SigNT, an accessional signature scheme with unmalleable transaction implementations. The key of SigNT is an improved interactive signature scheme for securely instant confirmation of transactions. Unlike standard signatures, this signature is generated by the owner and block producers. Combining it with several other optimizations (i.e., hash execution of intermediate transactions and secret-based claiming conditions), SigNT achieves complete resistance against malleability attacks in both the standard and contract transactions. As an example, we show an implementation in Bitcoin with the “providing a deposit” protocol. The security analysis and comparative experiments demonstrate that SigNT has the best resistance against malleability attacks than previous malleability solutions. Besides, better performance is achieved than other schemes.

With the proliferation of machine learning, the cloud server has been employed to collect massive data and train machine learning models. Several privacy-preserving machine learning schemes have been suggested recently to guarantee data and model privacy in the cloud. However, these schemes either mandate the involvement of the data owner in model training or utilize high-cost cryptographic techniques, resulting in excessive computational and communication overheads. Furthermore, none of the existing work considers the malicious behavior of the cloud server during model training. In this paper, we propose the first privacy-preserving and verifiable support vector machine training scheme by employing a two-cloud platform. Specifically, based on the homomorphic verification tag, we design a verification mechanism to enable verifiable machine learning training. Meanwhile, to improve the efficiency of model training, we combine homomorphic encryption and data perturbation to design an efficient multiplication operation for the encryption domain. A rigorous theoretical analysis demonstrates the security and reliability of our scheme. The experimental results indicate that our scheme can reduce computational and communication overheads by at least 43.94% and 99.58%, respectively, compared to state-of-the-art SVM training methods.

Federated learning (FL) has achieved state-of-the-art performance in distributed learning tasks with privacy requirements. However, it has been discovered that FL is vulnerable to adversarial attacks. The typical gradient inversion attacks primarily focus on attempting to obtain the client’s private input in a white-box manner, where the adversary is assumed to be either the client or the server. However, if both the clients and the server are honest and fully trusted, is the FL secure? In this paper, we propose a novel method called External Gradient Inversion Attack (EGIA) in the grey-box settings. Specifically, we concentrate on the point that public-shared gradients in FL are always transmitted through the intermediary nodes, which has been widely ignored. On this basis, we demonstrate that an external adversary can reconstruct the private input using gradients even if both the clients and the server are honest and fully trusted. We also provide a comprehensive theoretical analysis of the black-box attack scenario in which the adversary has only the gradients. We perform extensive experiments on multiple real-world datasets to test the effectiveness of EGIA. The outcomes of our experiments validate that the EGIA method is highly effective.

In response to the threat of adversarial examples, adversarial training provides an attractive option for improving robustness by training models on online-augmented adversarial examples. However, most existing adversarial training methods focus on improving the model’s robust accuracy by strengthening the adversarial examples but neglecting the increasing shift between natural data and adversarial examples, leading to a decrease in natural accuracy. To maintain the trade-off between natural and robust accuracy, we alleviate the shift from the perspective of feature adaption and propose a Feature Adaptive Adversarial Training (FAAT) optimizing the class-conditional feature adaption across natural data and adversarial examples. Specifically, we propose to incorporate a class-conditional discriminator to encourage the features to become(1)class-discriminative and(2)invariant to the change of adversarial attacks. The novel FAAT framework enables the trade-off between natural and robust accuracy by generating features with similar distribution across natural and adversarial data within the same class and achieves higher overall robustness benefiting from the class-discriminative feature characteristics. Experiments on various datasets demonstrate that FAAT produces more discriminative features and performs favorably against state-of-the-art methods.

Mobile crowdsensing (MCS) systems typically struggle to address the challenge of data aggregation, incentive design, and privacy protection, simultaneously. However, existing solutions usually focus on one or, at most, two of these issues. To this end, this paper presents CROWDFA, a novel paradigm for privacy-preserving MCS through federated analytics (FA), which aims to achieve a well-rounded solution encompassing data aggregation, incentive design, and privacy protection. Specifically, inspired by FA, CRWODFA initiates an MCS computing paradigm that enables data aggregation and incentive design. Participants can perform aggregation operations on their local data, facilitated by CROWDFA, which supports various common data aggregation operations and bidding incentives. To address privacy concerns, CROWDFA relies solely on an efficient cryptographic primitive known as additive secret sharing to simultaneously achieve privacy-preserving data aggregation and privacy-preserving incentive. To instantiate CROWDFA, this paper presents a privacy-preserving data aggregation scheme (PRADA) based on CROWDFA, capable of supporting a range of data aggregation operations. Additionally, a CROWDFA-based privacy-preserving incentive mechanism (PRAED) is designed to ensure truthful and fair incentives for each participant, while maximizing their individual rewards. Theoretical analysis and experimental evaluations demonstrate that CROWDFA protects participants’ data and bid privacy while effectively aggregating sensing data. Notably, CROWDFA outperforms state-of-the-art approaches by achieving up to 22 times faster computation time.

Community structure is a typical characteristic of complex networks. Finding communities in complex networks has many important applications, such as the advertisement and recommendation based on social networks and the discovery of new protein molecules in biological networks, which make it a hot topic in the field of complex network analysis. With the increasing concerns about the leakage of personal privacy, discovering communities spread across the local networks owned by multiple participants accurately while preserving each participant’s privacy has become an emerging challenge in distributed community detection. In this article, we propose a general federated graph learning model for privacy-preserving distributed graph learning and develop two federated clique percolation algorithms (CPAs) based on it to discover overlapping communities distributed across multiple participants’ local networks without disclosing any participant’s network privacy. Homomorphic encryption and hash operation are used in combination to protect the privacy of the vertices and edges of each local network. Furthermore, vertex attributes are involved in the calculation of clique similarity and clique percolation when dealing with attributed networks. The experimental results on real-world and artificial datasets demonstrate that the proposed algorithms achieve identical results to those of their stand-alone counterparts and more than 200% higher accuracy than the simple distributed CPAs without federating learning.

Federated learning is good for building better cooperative intelligent transportation system (C-ITS). Intellectual property protection in C-ITS brings many benefits to all vehicles. Although the protection of model intellectual property by watermark has received much research attention, the existing works only deploy watermark in centralized models. Due to the difference of watermark distribution among vehicles, the global model accuracy of watermark in federated learning is significantly reduced or the local watermark is invalid. To solve these problems, we propose a multi-party entangled watermark algorithm in federated learning. Specifically, in the local training, we propose a watermark enhancement algorithm, which solves the problem of local watermark failure. Then, in the global aggregation, we propose an entanglement aggregation algorithm, which solves the problem of a great loss of global model accuracy. We conduct extensive experiments on public datasets to show the superiority of our proposal. The results show that our scheme can obtain more than 16% and 31% advantages in model accuracy and watermark success rate, respectively, compared with existing watermark schemes in federated learning.

Social trust assessment that characterizes a pairwise trustworthiness relationship can spur diversified applications. Extensive efforts have been put in exploration, but mainly focusing on applying graph convolutional network to establish a social trust evaluation model, overlooking user feature factors related to context-aware information on social trust prediction. In this article, we aim to design a new trust assessment framework GATrust which integrates multi-aspect properties of users, including user context-specific information, network topological structure information, and locally-generated social trust relationships. GATrust can assigns different attention coefficients to multi-aspect properties of users in online social networks, for improving the prediction accuracy of social trust evaluation. The framework can then learn multiple latent factors of each trustor-trustee pair to establish a social trust evaluation model, by fusing graph attention network and graph convolution network. We conduct extensive experiments on two popular real-world datasets and the results exhibit that our proposed framework can improve the precision of social trust prediction, outperforming the state-of-the-art in the literature by 4.3% and 5.5% on both two datasets, respectively.

With increasingly popular GPS-equipped mobile devices (e.g., smartphones, tablets, laptops), massive spatio-textual data has been outsourced to cloud servers for storage and analysis such as spatial keyword search. However, existing privacy-preserving spatial keyword query schemes only support coarse-grained non-temporal access control in single-user sharing scenarios, which does not scale well in time-related scenes such as message valid period. To solve the above issues, we propose Privacy-preserving Boolean Range Query with Temporal access control in mobile computing (PBRQ-T). Specifically, we first achieve PBRQ with linear search complexity using the adapted Gray code, Bloom filter, and Katz-Sahai-Waters encryption. Then, we provide fine-grained and temporal access control in PBRQ based on the forward/backward derivation function and attribute-based encryption, where PBRQ is executed only when the spatio-textual data is accessible. Finally, an enhanced PBRQ-T (i.e., PBRQ-T+) with faster-than-linear search complexity is proposed by constructing a Quadtree index structure. Our formal security analysis shows that data privacy and index privacy can be guaranteed during the query process. Our extensive experiments using a real-world dataset demonstrate the efficiency and feasibility of our schemes.

To ensure the security of outsourced data without affecting data availability, one can use Symmetric Searchable Encryption (SSE) to achieve search over encrypted data. Considering that query users may search with misspelled words, the fuzzy search should be supported. However, conventional privacy-preserving fuzzy multi-keyword search schemes are incapable of achieving the result verification and adaptive security. To solve the above challenging issues, in this paper we propose a Verifiable Fuzzy multi-keyword Search scheme with Adaptive security (VFSA). VFSA first employs the locality sensitive hashing to hash the misspelled and correct keywords to the same positions, then designs a twin Bloom filter for each document to store and mask all keywords contained in the document, next constructs an index tree based on the graph-based keyword partition algorithm to achieve adaptive sublinear retrieval, finally combines the Merkle hash tree structure with the adapted multiset accumulator to check the correctness and completeness of search results. Our formal security analysis shows that VFSA is secure under the IND-CKA2 model and achieves query authentication. Our empirical experiments using the real-world dataset demonstrate the practicality of VFSA.

With the increasing popularity of GPS-equipped mobile devices in cloud-assisted fog computing scenarios, massive spatio-textual data is generated and outsourced to cloud servers for storage and analysis. Existing privacy-preserving range query or ranked keyword search schemes does not support a unified index, and are just applicable for the symmetric environment where all users sharing the same secret key. To solve this issue, we propose aPrivacy-preservingRankedSpatial keywordQuery in mobile cloud-assistedFog computing (PRSQ-F). Specifically, we design a novel comparable product encoding strategy that combines both spatial and textual conditions tightly to retrieve the objects in query range and with the highest textual similarity. Then, we use a new conversion protocol and attribute-based encryption to support privacy-preserving retrieval and malicious user traceability in the asymmetric environment where different query users have different keys. Furthermore, we construct an R-tree-based index to achieve faster-than-linear retrieval. Our formal security analysis shows that data security can be guaranteed. Our empirical experiments using a real-world dataset demonstrate the efficiency and feasibility of PRSQ-F.

The widespread usage of wearables to provide healthcare services prompts the need for secure group communication among multiple devices using group keys. Gait-based group key establishment schemes are either vulnerable to video attacks, or fail to offer a secure group key update mechanism when group device changes. In this paper, we present an electrocardiogram (ECG) signals based group device pairing protocol, which can strengthen the security and reduce the overhead of wearables. Specifically, we first design a robust and lightweight fuzzy extractor that supports secure and efficient group device association between wearables. Meanwhile, we propose Improved Martingale Randomness Extraction (IMRE) algorithm, which utilizes the trend of InterPulse Interval (IPI) from ECG signal to extract high-entropy keys. Then we present a membership management mechanism that enables group key dynamic update when group device changes. Finally, we simulate our protocol and evaluate the accuracy and efficiency by various experiments. The experimental results demonstrate that the proposed work is robust and efficient, and the threat model-based security analysis shows that the proposed protocol can prevent both active and passive attacks.

As an emerging sensing data collection paradigm, mobile crowdsensing (MCS) enjoys good scalability and low deployment cost but raises privacy concerns. In this paper, we propose a privacy-preserving MCS system calledCrowdFLby seamlessly integrating federated learning (FL) into MCS. At a high level, in order to protect participants’ privacy and fully explore participants’ computing power, participants inCrowdFLlocally process sensing data via FL paradigm and only upload encrypted training models to the server. To this end, we design a secure aggregation algorithm (SecAgg) through the threshold Paillier cryptosystem to aggregate training models in an encrypted form. Also, to stimulate participation, we present a hybrid incentive mechanism combining the reverse Vickrey auction and posted pricing mechanism, which is proved to be truthful and fail. Results of theoretical analysis and experimental evaluation on a practical MCS scenario (human activity recognition) show thatCrowdFLis effective in protecting participants’ privacy and is efficient in operations. In contrast to existing solutions,CrowdFLis 3× faster in model decryption and improves an order of magnitude in model aggregation.

Symmetric Searchable Encryption (SSE), as an ideal primitive, can ensure data privacy while supporting retrieval over encrypted data. However, existing multi-user SSE schemes require the data owner to share the secret key with all query users or always be online to generate search tokens. While there are some solutions to this problem, they have at least one weakness, such as non-supporting conjunctive query, result decryption assistance of the data owner, and unauthorized access. To solve the above issues, we propose an O wner-free Di stributed S ymmetric searchable encryption supporting C onjunctive query (ODiSC). Specifically, we first evaluate the Learning-Parity-with-Noise weak Pseudorandom Function (LPN-wPRF) in dual-cloud architecture to generate search tokens with the data owner free from sharing key and being online. Then, we provide fine-grained conjunctive query in the distributed architecture using additive secret sharing and symmetric-key hidden vector encryption. Finally, formal security analysis and empirical performance evaluation demonstrate that ODiSC is adaptively simulation-secure and efficient.

Person re-identification (Person Re-ID) is widely regarded as a promising technique to identify a target person through surveillance cameras in the wild. Nevertheless, person Re-ID leads to severe personal image privacy concerns as personal images are stipulated by laws and guidelines as private data. To address these concerns, this article explores the first solution for building a privacy-preserving person Re-ID system. Specifically, this article formulizes privacy-preserving person Re-ID as similarity metrics of encrypted feature vectors because the underlying operation of person Re-ID is to compute the similarity of feature vectors that are extracted from person images by a machine learning model. However, feature vectors are generally denoted by floating-point numbers. To this end, this article exploits a series of new encoding mechanisms and secure batch computing protocols to encrypt floating-point feature vectors and achieve the underlying operation of person Re-ID. Rigorous theoretical analyses demonstrate that this work achieves person Re-ID without compromising any personal image privacy. Furthermore, the proposed secure batch protocols significantly enhance the performance of privacy-preserving person Re-ID while outputting the same precision as the previous method.

Proof of Stake powered blockchains account for general trends in existing consensus mechanisms. However, existing PoS protocols are vulnerable to the nothing at stake and long range attacks, which allow attackers to gain unfair shares based on costless simulations and malicious sale information. In a decentralized setting, these securities are limited as each node is unregulated. To address these problems, we introduce a proof-of-hardware-stake (PohS) consensus mechanism and a regulatory mechanism based on a consortium blockchain. Our approach is implemented in a sharding blockchain to scale the consensus. Since any node on the network cannot fake information, the blockchain trustless won not be decreased by the reliance on a consortium blockchain. Under the competing rule of PohS consensus mechanism, adversaries can issue the long range attack with at most$10^{-3}$probability. The regulatory mechanism implements the regulation of costless simulations at the nothing stake attack. We prove that our design is secure (e.g.,51% and selfish mining) against adversarial stakes less than 51% by adopting the square root of stakes for competition. Our proof also highlights the security of double-spending and long range attacks. Simulations are conducted to compare the efficiency of our approach with Ethereum and Ouroboros.

With the popularity of location based services, spatial keyword query has become an important application. In order to save the storage and computational costs, most data owners will outsource the data to the cloud server, but this will lead to two problems, such as privacy leakage and heavy network bandwidth burden. To solve above problems, we propose a Privacy-preserving top-k Spatial Keyword queries based on Fog computing, namly PSKF. To further improve the search efficiency, we use the IR-tree to build the index and store it in the cloud server. Each fog server also saves a different subtree of the IR-tree, so that we can decide which fog server to participate in the query by pruning. Formal security analysis shows that our proposed PSKF achieves Indistinguishability under Known-Plaintext Attacks (IND-KPA), and extensive experiments demonstrate that our proposed scheme is efficient and feasible in practical applications.

In machine learning (ML), the massive data processing and dense computations based on matrices make outsourced inference computation a growing trend. The unreliability of cloud platforms makes privacy protection and inference correctness increasingly important in outsourced computations. Unfortunately, current works cannot provide an effective verification mechanism and privacy protection for outsourcing linear computing simultaneously. To address the issue, in the service architectures with malicious behaviors (such as curiosity, dishonesty, and collusion), we propose privacy-preserving and verifiable outsourcing inference computing (PPVLC) for the most fundamental linear computations in ML. PPVLC uses secret sharing and blinding techniques to protect privacy and achieve secure computation of matrix linear computation. Meanwhile, bilinear mapping based on matrix digest is utilized to verify computation correctness, ensuring the trustworthiness of the service. Security analysis and experiments demonstrate the reliability of our scheme and service efficiency.

Spatial keyword queries have attracted much attention over the past decade due to the popularity of location-based services and social networks, which brings great economic benefits. Geo-textual data are encrypted-and-delegated to public clouds for efficient management and utilization while preventing potential data leakage. However, it is still challenging to solve securerangespatialkeyword queries on encrypted data since existing works are either vulnerable or inefficient. In this paper, a secure hybrid index is built to implement efficient filtering, by embedding nodes’ paths in a novel symmetrical kd-tree into inverted indexes and employing only lightweight cryptographic techniques. A concrete scheme RASK is constructed on the secure index by utilizing only a little storage and computing resources of clients. Furthermore, RASK+ is proposed based on secure virtual technology by migrating all storage burdens from clients to public clouds. Both schemes are theoretically proved to beindistinguishable under adaptive chosen keyword attacks(IND-CKA2). Through experimental evaluations on three real datasets within consistent environments, both schemes reduce the response time by about 50%-80% compared to state-of-the-art solutions (i.e., SKSE, LSKQ, etc.). The storage overheads for the cloud are also reduced by about 0.5-2 orders of magnitude.

Member Inference Attack (MIA) is a key measure for evaluating privacy leakage in Machine Learning (ML) models, aiming to distinguish private members from non-members by training the attack model. In addition to the traditional MIA, the recently proposed Generative Adversarial Network (GAN)-based MIA can help the adversary know the distribution of the victim's private dataset, thereby significantly improving attack accuracy. For traditional attacks and this new type of attack, previous defense schemes cannot handle the trade-off between privacy and utility well. To this end, we propose a defense solution using multi-model ensemble framework. Specifically, we train multiple submodels to hide membership signals and resist MIA, achieving reduced privacy leakage while guaranteeing the effectiveness of the target model. Our security analysis shows that our scheme can provide privacy protection while preserving model utility. Experimental results on widely used datasets show that our scheme can effectively resist MIAs with negligible utility loss.

Ranked keyword search over encrypted data has been extensively studied in cloud computing as it enables data users to find the most relevant results quickly. However, existing ranked multi-keyword search solutions cannot achieve efficient ciphertext search and dynamic updates with forward security simultaneously. To solve the above problems, we first present a basic Machine Learning-based Ranked Keyword Search (ML-RKS) scheme in the static setting by using the k-means clustering algorithm and a balanced binary tree. ML-RKS reduces the search complexity without sacrificing the search accuracy, but is still vulnerable to forward security threats when applied in the dynamic setting. Then, we propose an Enhanced ML-RKS (called ML-RKS$^{+}$) scheme by introducing a permutation matrix. ML-RKS$^{+}$prevents cloud servers from making search queries over newly added files via previous tokens, thereby achieving forward security. The security analysis proves that our schemes protect the privacy of indexes, query tokens and keywords. Empirical experiments using the real-world dataset demonstrate that our schemes are efficient and feasible in practical applications.

The encrypted image retrieval technique allows users to retrieve images in an encrypted manner without decrypting images. However, most of the existing schemes still are vulnerable to security threats and inefficiency, caused by malicious users and inefficient feature extraction methods, respectively. To this end, we propose a traceable encrypted image retrieval in the multi-user setting in this article, termed as MU-TEIR. First, MU-TEIR employs a convolutional neural network VGG16 to extract image feature vectors and calculate the mean and variance of the feature vectors to construct the index, then encrypts index with the distributed two trapdoors public-key cryptosystem. After that, MU-TEIR protects image content by encrypting each image pixel with a standard stream cipher. Furthermore, MU-TEIR utilizes a watermark-based mechanism to prevent malicious query users from maliciously distributing images. Detailed security analysis shows that MU-TEIR protects the outsourced images and indexes security as well as query privacy, and can track malicious users. Experimental results verify effectiveness of MU-TEIR.

Federated learning (FL) was once considered secure for keeping clients’ raw data locally without relaying on a central server. However, the transmitted model weights or gradients still reveal private information, which can be exploited to launch various inference attacks. Moreover, FL based on deep neural networks is prone to the curse of dimensionality. In this paper, we propose a compressed and privacy-preserving FL scheme in DNN architecture by using Compressive sensing and Adaptive local differential privacy (called as CAFL). Specifically, we first compress the local models by using Compressive Sensing (CS), then adaptively perturb the remaining weights according to their different centers of variation ranges in different layers and their own offsets from corresponding range centers by using Local Differential Privacy (LDP), finally reconstruct the global model almost perfectly by using the reconstruction algorithm of CS. Formal security analysis shows that our scheme achieves ϵ-LDP security and introduces zero bias to estimating average weights. Extensive experiments using MINIST and Fashion-MINIST datasets demonstrate that our scheme with minimum compression ratio 0.05 can reduce the number of parameters by 95%, and with a lower privacy budget ϵ = 1 can improve the accuracy by 80% on MINIST and 12.7% on Fashion-MINIST compared with state-of-the-art schemes.

With the future 6G era, spiking neural networks (SNNs) can be powerful processing tools in various areas due to their strong artificial intelligence (AI) processing capabilities, such as biometric recognition, AI robotics, autonomous drive, and healthcare. However, within Cyber Physical System (CPS), SNNs are surprisingly vulnerable to adversarial examples generated by benign samples with human-imperceptible noise, this will lead to serious consequences such as face recognition anomalies, autonomous drive-out of control, and wrong medical diagnosis. Only by fully understanding the principles of adversarial attacks with adversarial samples can we defend against them. Nowadays, most existing adversarial attacks result in a severe accuracy degradation to trained SNNs. Still, the critical issue is that they only generate adversarial samples by randomly adding, deleting, and flipping spike trains, making them easy to identify by filters, even by human eyes. Besides, the attack performance and speed also can be improved further. Hence, Spike Probabilistic Attack (SPA) is presented in this paper and aims to generate adversarial samples with more minor perturbations, greater model accuracy degradation, and faster iteration. SPA uses Poisson coding to generate spikes as probabilities, directly converting input data into spikes for faster speed and generating uniformly distributed perturbation for better attack performance. Moreover, an objective function is constructed for minor perturbations and keeping attack success rate, which speeds up the convergence by adjusting parameters. Both white-box and black-box settings are conducted to evaluate the merits of SPA. Experimental results show the model's accuracy under white-box attack decreases by 9.2S%~31.1S% better than others, and average success rates are 74.87% under the black-box setting. The experimental results indicate that SPA has better attack performance than other existing attacks in the white-box and better transferability performance in the black-box setting,

Adversarial training is believed to be the most robust and effective defense method against adversarial attacks. Gradient-based adversarial attack methods are generally adopted to evaluate the effectiveness of adversarial training. However, in this paper, by diving into the existing adversarial attack literature, we find that adversarial examples generated by these attack methods tend to be less imperceptible, which may lead to an inaccurate estimation for the effectiveness of the adversarial training. The existing adversarial attacks mostly adopt gradient-based optimization methods and such optimization methods have difficulties in searching the most effective adversarial examples (i.e., the global extreme points). On the contrast, in this work, we propose a novel Non-Gradient Attack (NGA) to overcome the above-mentioned problem. Extensive experiments show that NGA significantly outperforms the state-of-the-art adversarial attacks on Attack Success Rate (ASR) by 2% ∼ 7%.

Compound screening is a key step in the development of new drugs. Current high-throughput screening methods cannot be widely adopted by laboratories due to their expensive equipment and low efficiency. The booming deep learning in recent years has provided a new answer to this question. The message passing neural network (MPNN) can directly predict molecular properties from molecular structure so that compound screening can be completed without experimentation. In the face of large-scale molecular data, outsourcing this task to a professional cloud server can further accelerate prediction efficiency and reduce costs. In order to solve the privacy protection problem of computing on cloud servers, we propose a 3-party molecular structure properties inference privacy protection framework SecMPNN based on additive secret sharing. We design brand-new cryptographic protocols to ensure the privacy and security in the prediction process, and through experiments show that the single inference time of our protocol on different networks is 40.85% faster than CRYPTEN and 18.5% faster than SecureNN.

Backdoor injection attack is an emerging threat to the security of neural networks, however, there still exist limited effective defense methods against the attack. In this paper, we propose BAERASER, a novel method that can erase the backdoor injected into the victim model through machine unlearning. Specifically, BAERASER mainly implements backdoor defense in two key steps. First, trigger pattern recovery is conducted to extract the trigger patterns infected by the victim model. Here, the trigger pattern recovery problem is equivalent to the one of extracting an unknown noise distribution from the victim model, which can be easily resolved by the entropy maximization based generative model. Subsequently, BAERASER leverages these recovered trigger patterns to reverse the backdoor injection procedure and induce the victim model to erase the polluted memories through a newly designed gradient ascent based machine unlearning method. Compared with the previous machine unlearning solutions, the proposed approach gets rid of the reliance on the full access to training data for retraining and shows higher effectiveness on backdoor erasing than existing fine-tuning or pruning methods. Moreover, experiments show that BAERASER can averagely lower the attack success rates of three kinds of state-of-the-art backdoor attacks by 99% on four benchmark datasets.

Machine unlearning is a significant part of machine learning security because machine learning models are not immune to attacks such as poisoning attacks. In addition, various studies have proved that it is feasible to obtain training set information from the model, which can lead to leakage of user data privacy. Therefore, there is an urgent need for a method to remove specific data from the model training set. Naive retraining will bring huge time and resource costs, while SISA can achieve a balance between unlearning cost and model performance to a certain extent by dividing the dataset into multiple independent shards. As forgotten data grows, the performance of SISA is still unable to meet the actual needs. In this paper, we propose a method, which dynamically selects the shards that need to be retrained. First, we divide the dataset into multiple independent shards, when the forgotten data makes multiple shards need to be retrained at the same time, our approach is to mix these affected shards together, and then train the mixed shards individually to achieve global forgetting. The simulation results show that compared with SISA, we can get more than 3× speedup on different datasets, and the accuracy of the aggregation model is also improved by 0.5% and 2.1% on MNIST and CIFAR10, respectively.

Summary Malware detection is indispensable to cybersecurity. However, with the advent of new malware variants and scenarios with few and imbalanced samples, malware detection for various complex scenarios has been a very challenging problem. In this article, we propose a malware detection method based on image analysis and generative adversarial networks, named MadInG, which can improve the accuracy of malware detection for insufficient samples, sample imbalance, and new variants scenarios. Specifically, we first generate fixed‐size grayscale images of malware to reduce the workload of feature engineering or the involvement of domain expert knowledge on malware detection. Then we introduce auxiliary classifier generative adversarial networks into malware detection to enhance the generalization ability of the detector. Finally, we construct a variety of malware scenarios and compare our proposed method with existing popular detection methods. Extensive experimental results demonstrate that our method achieves high accuracy and well balance in malware detection for different scenarios, especially, the detection rate of malware variants reaches 99.5%.

In recent years, the appearance of graph convolutional networks (GCNs) provides a new idea for graph structure data processing. Because of that, they can learn excellent user and item embedding by using cooperative signals of high-order neighbors, and the GCNs technique shows great potential in the recommendation. The common problem with the bulk of GCN-based models is that it appears the situation of performance degradation during the stacking of network layers. The recently proposed IMP-GCN alleviates this problem to some extent. It aims to avoid the influence of downside information from high-order propagation on embedding learning. However, we consider that it ignores the multi-interest factor, in which users may have different interests. In this paper, we present a multi-interest GCN(MI-GCN) model for a recommendation, and it conducts high-order graph convolution operations in three sets of subgraphs. Users with similar interests and the corresponding interaction items belong to the identical subgraph. As for the formation of the subgraph, we adopt two varied clustering methods and the user feature to form a subgraph generation mechanism. This mechanism can generate three groups of differential subgraphs to divide users into multi-interest groups and make subgraph division more reasonable. We carry out massive experiments on three real-world datasets, demonstrating the effectiveness of our model. Experimental results confirm that our presented MI-GCN outperforms the state-of-the-art GCN-based recommendation models.

Cover Caption: The cover image is based on the Research Article Active forgetting via influence estimation for neural networks by Xianjia Meng et al., https://doi.org/10.1002/int.22981.

The rapidly exploding of user data, especially applications of neural networks, involves analyzing data collected from individuals, which brings convenience to life. Meanwhile, privacy leakage in the applications as a potential threat needs to be addressed urgently. However, removing private information from models is difficult once the user's sensitive data enters machine learning models, particularly neural networks. Most of the previous amnestic methods based on retraining require full access to the training set of the target model and have limited improvements in computational resources and time improvement. In this paper, we propose Scrubber, which removes sensitive data from the original model via influence estimation to produce an unlearning model that is approximately indistinguishable from the retrained model. S crubber builds on the essential concept of influence function and reformulates the influence estimation as a closed-form update of forgetting. For learned models with strictly convex loss functions, our approach theoretically guarantees the effectiveness of forgetting while empirically demonstrating forgetting performance. For models with non-convex losses, we relax strictly convex assumptions by applying a damping term that allows us to make approximate estimates with negligible errors from the original assumption. Furthermore, experiments show that S crubber only causes less than 1% and 3% accuracy drop with more than 80% forgetting rate on average for logistic regression models and convolutional neural networks. The accuracy drop is reduced by 2%–3% compared to most state-of-the-art methods.

Nowadays, the impressive performance of deep neural networks (DNNs) greatly advances the development of Internet of Things (IoT) in diverse scenarios. However, the exceptional vulnerability of DNNs to adversarial attack leads IoT devices to be exposed to potential security issues. Up to now, since adversarial training empirically remains robust against gradient-based adversarial attacks, it is believed to be the most effective defense method. In this article, we find that adversarial examples generated by gradient-based adversarial attacks tend to be less imperceptible induced by the gradient-based optimization methods (adopted in the attacks) being difficult on searching the most effective adversarial examples (i.e., the global extreme points), which may lead to an inaccurate estimation for the effectiveness of the adversarial training. To overcome the inherent defect of gradient-based adversarial attacks, we propose a novel adversarial attack named nongradient attack (NGA), of which search strategy is effective but no longer depends on gradients to enhance the threat of adversarial examples. In detail, NGA first initializes the adversarial examples outside, rather than inside, of decision boundary to make them misclassified by the model and then, under without violation of misclassified condition, adjusts the adversarial examples toward the crafted direction to close the original examples. Extensive experiments show that NGA significantly outperforms the state-of-the-art adversarial attacks on attack success rate (ASR) by 2%–7%. Moreover, we propose a new evaluation metric, i.e., composite criterion (CC) based on both ASR and accuracy, to better measure the effectiveness of adversarial training. In the experiments, CC has shown to be a more comprehensive yet appropriate evaluation metric.

Ciphertext retrieval under heterogeneous data sets is a critical concern in the cloud-assisted Internet of Things (IoT). Previous ciphertext retrieval schemes eliminate computation burden and security concerns to some extent, but cannot support the encrypted heterogeneous data sets. To solve this problem, in this article we propose a transparent ciphertext retrieval system regardless of programming language, accessible platforms, and heterogeneity of data sets. The retrieval system is a novel combination of the proposed access and integration middleware with a current encrypted cloud database system. The middleware enables cross-language and cross-platform queries over various database systems, besides, it schedules the designed data integration method in heterogeneous databases to realize cross-database queries over the encrypted cloud data sets. The proposed ciphertext retrieval system achieves efficient data sharing among different IoT applications with various database systems. We prove that the system guarantees data security by avoiding malicious hackers. Extensive experiments show that our design is efficient and feasible in practice.

Controller area network (CAN) bus anomaly detection on the Internet of Vehicles (IoV) is a topic of ongoing interest and increasing importance, particularly as IoV becomes commonplace. However, existing abnormal detection schemes are not ideal due to the lack of abnormal data in IoV and the difficulty of parsing the diverse message rules in existing vehicles. While single-classification of the support vector domain description (SVDD) algorithm can detect abnormalities only with normal message information, the approach has a high rate of false negatives when deployed directly in the in-vehicle network environment. In addition, the real-time data generation (e.g., IoV messages) compounds the challenge of designing effective detection approaches. Therefore, this article proposes a mechanism for car networking message classification for a broad range of data, and establishes a weak model for many simple redundant data in the vehicle Intranet. The detection can reduce the time and computation costs of detection while ensuring accuracy. Then, this article proposes two improved SVDD schemes: 1) M-SVDD scheme, which adds the Markov chain to detect time-related messages and 2) G-SVDD scheme, which maps the kernel function to the Gaussian kernel function to reduce the redundant area of the model and the false-negative rate. The experimental results show that our proposed schemes have higher accuracy, recall rate, and fewer computation overhead.

Internet of Things (IoT) devices and systems are becoming increasingly commonplace, and as such systems scale up, so do the computational and storage requirements. Hence, one recent trend is to outsource data from IoT devices to remote systems. To facilitate both ciphertext retrieval and data confidentiality in the outsourced data, a number of searchable encryption (SE) approaches have been proposed in the literature. However, due to limited keyword space, a number of SE schemes are vulnerable to keyword guessing attacks (KGAs). In addition, existing SE approaches generally do not consider the hierarchical structure in which users at different levels require varying access privileges. Furthermore, existing SE schemes seldom provide time-controlled access control. Therefore, in this article, we propose a time-controlled hierarchical multikeyword search by using a double-server architecture to mitigate KGA. In our approach, we also build a public key tree to support different access permissions for hierarchical users. Formal security analysis shows that our scheme is secure, and extensive experiments demonstrate that our scheme is practical.

Distributed spatial cloaking (DSC) enables users to enjoy precise location-based service (LBS) with location privacy preserving. An incentive mechanism is necessary to encourage users to cooperate. However, due to the inappropriate design of incentive mechanisms, the existing works cause low user benefits and fail to encourage users, ruining the expected incentive effect. Moreover, introducing a third party to manage users’ information also causes the existing works to disclose users’ privacy and be unpractical. To address these issues, we propose a utility-aware incentive mechanism-based distributed spatial cloaking (RESAT). By the idea of utility theory and optimization theory, RESAT devises basic and extended incentive mechanisms. The two mechanisms for assuming that all users are honest and that malicious users provide unreasonable locations. RESAT proposes an incentive mechanism-based cloaking cooperation without a third party, incorporating the developed mechanisms based on the blind signature. Theoretical analysis indicates that RESAT achieves incentive compatibility and is secure. Extensive experiments on the real data set show that compared with the existing works, RESAT enables 1 time more users to cooperate at best while eliminating the malicious behaviors that provide unreasonable locations. The required DSC construction time delay is limited.

Encrypted image retrieval is a promising technique for achieving data confidentiality and searchability the in cloud-assisted Internet of Things (IoT) environment. However, most of the existing top-$k$ranked image retrieval solutions have low retrieval efficiency and may leak the values and orders of similarity scores to the cloud server. Hence, if a malicious server learns user background information through some improper means, then the malicious server can potentially infer user preferences and guess the most similar image content according to similarity scores. To solve the above challenges, we propose a privacy-preserving threshold-based image retrieval scheme using the convolutional neural network (CNN) model and a secure$k$-nearest neighbor (kNN) algorithm, which improves the retrieval efficiency and prevents the cloud server from learning the values and orders of similarity scores. Formal security analysis shows that our proposed scheme can resist both ciphertext-only attack (COA) and chosen-plaintext attack (CPA), and extensive experiments demonstrate that our proposed scheme is efficient and feasible for real-world data sets.

Collaborative perception enables autonomous vehicles to exchange sensor data among each other to achieve cooperative object classification, which is considered an effective means to improve the perception accuracy of connected autonomous vehicles (CAVs). To protect information privacy in cooperative perception, we propose a lightweight, privacy-preserving cooperative object classification framework that allows CAVs to exchange raw sensor data (e.g., images captured by HD camera), without leaking private information. Leveraging chaotic encryption and additive secret sharing technique, image data are first encrypted into two ciphertexts and processed, in the encrypted format, by two separate edge servers. The use of chaotic mapping can avoid information leakage during data uploading. The encrypted images are then processed by the proposed privacy-preserving convolutional neural network (P-CNN) model embedded in the designed secure computing protocols. Finally, the processed results are combined/decrypted on the receiving vehicles to realize cooperative object classification. We formally prove the correctness and security of the proposed framework and carry out intensive experiments to evaluate its performance. The experimental results indicate that P-CNN offers exactly almost the same object classification results as the original CNN model, while offering great privacy protection of shared data and lightweight execution efficiency.

Fog-assisted Internet of Things (IoT) can outsource the massive data of resource-constraint IoT devices to cloud and fog nodes (FNs). Meanwhile, it enables convenient and low time-delay data-sharing services, which relies heavily on high security of data confidentiality and fine-grained access control. Many efforts have been focused on this urgent requirement by leveraging ciphertext-policy attribute-based encryption (CP-ABE). However, when deployed in fog-assisted IoT systems for secure data sharing, it remains a challenging problem of how to preserve attribute privacy of access policy, and trace-then-revoke traitors (i.e., malicious users intending to leak decryption keys for illegal profits) efficiently and securely in such a large scale and decentralized environment with resource-constraint user devices, especially in consideration of misbehaving cloud and FNs. Therefore, in this article, we propose a revocable and privacy-preserving decentralized data-sharing framework (RPDDSF) by designing a large universe and multiauthority CP-ABE scheme with fully hidden access policy for secure data sharing in IoT systems to achieve user attribute privacy preserving with unbounded attribute universe and key escrow resistance suitable for large scale and decentralized environment. Based on this, with RPDDSF, anyone can efficiently expose the traitors and punish them by forward/backward secure revocation. Besides, RPDDSF is able to guarantee data integrity for both data owners (DOs) and users to resist misbehaving cloud and FNs, alongwith low computation overhead for resource-constraint devices. Finally, RPDDSF is proven to be secure with detailed security proofs, and its high efficiency and feasibility are demonstrated by extensive performance evaluations.

For group signature (GS) supporting membership revocation, verifier-local revocation (VLR) mechanism seems to be a more flexible choice, because it requires only that verifiers download up-to-date revocation information for signature verification, and the signers are not involved. As a post-quantum secure cryptographic counterpart of classical number-theoretic cryptographic constructions, the first lattice-based VLR group signature (VLR-GS) was introduced by Langlois et al. (2014). However, none of the contemporary lattice-based VLR-GS schemes provide backward unlinkability (BU), which is an important property to ensure that previously issued signatures remain anonymous and unlinkable even after the corresponding signer (i.e., member) is revoked. In this study, we introduce the first lattice-based VLR-GS scheme with BU security (VLR-GS-BU), and thus resolve a prominent open problem posed by previous works. Our new scheme enjoys an $${\cal O}\left( {\log \,N} \right)$$ factor saving for bit-sizes of the group public-key (GPK) and the member’s signing secret-key, and it is free of any public-key encryption. In the random oracle model, our scheme is proven secure under two well-known hardness assumptions of the short integer solution (SIS) problem and learning with errors (LWE) problem.

Recently, Graph Neural Networks (GNNs) have been widely used for fraud detection. GNNs first generate node embedding by aggregating neighboring information under different relations, and then use the final node embedding to detect the node’s suspiciousness. However, traditional GNNs employing only a single type of aggregator fail to capture neighbor information from multiple perspectives and treating different relations equally inevitably weakens the semantic information of heterogeneous graphs. Meanwhile, expressive ability of GNNs is limited by using conventional concatenating or averaging operations to update the center node. Also, camouflaged entities could damage GNN-based models. To handle these problems, a novel heterogeneous GNN model calledMultiple Aggregators and Feature Interactions Network(MAFI) is proposed in this paper to conduct fraud detection tasks. Concretely, multiple types of aggregators are applied on different relations to aggregate neighbor information and aggregator-level attention is utilized to learn the importance of different aggregators. Also, relation-level attention is leveraged to learn the importance of each relation. Besides, conventional update operations are replaced with vector-wise implicit and explicit feature interactions. Moreover, a trainable neighbor sampler is employed to filter camouflaged fraudsters. Comprehensive experiments on two real-world fraud datasets indicate that the proposed MAFI outperforms existing GNN-based fraud detectors.

The increasing awareness in privacy has partly contributed to the renewed interest in privacy-preserving encrypted image retrieval, and designing for outsourced images stored on cloud servers, etc. However, there are some limitations in these existing schemes such as low retrieval accuracy, low retrieval efficiency, and less efficient result verification in the dynamic setting. Therefore, in this paper we present a novel Dynamic Verifiable Retrieval over Encrypted Images (DVREI) scheme. First, a pre-trained Convolutional Neural Network (CNN) model is utilized to extract image features to improve retrieval accuracy. Then, an encrypted index based on the K-means clustering algorithm is designed to improve retrieval efficiency. Finally, a dynamic verification tree based on the chameleon hash is used to verify the correctness of the retrieval results and support dynamic updates. We theoretically and experimentally evaluate the security and performance of DVREI to demonstrate its practicability.

Anomaly detection offers a powerful approach to identifying unusual activities and uncommon behaviors in real-world video scenes. At present, convolutional neural networks (CNN) have been widely used to tackle anomalous events detection, which mainly rely on its stronger ability of feature representation than traditional hand-crafted features. However, massive video data and high cost of CNN model training are a challenge to achieve satisfactory detection results for resource-limited users. In this article, we propose a secure video anomaly detection framework (SecureAD) based on CNN. Specifically, we introduce additive secret sharing to design several calculation protocols for achieving safe CNN training and video anomaly detection. Besides, we propose a Bloom filter based fine-grained access control policy to authenticate legitimate users, without leaking the privacy of raw personal attributes. In addition, edge computing instead of cloud computing is integrated into the architecture to reduce response time between servers and users in an outsourced environment. Finally, we prove that the proposed SecureAD achieves secure video anomaly detection without compromising the privacy of the related data. Also, the simulation results demonstrate the effectiveness and security of our SecureAD.

Searchable symmetric encryption (SSE) enables a user to outsource a private dataset to a cloud server in encrypted form while retaining the ability to search over the encrypted outsourced data. The existing SSE schemes improve the search and safety performances from different perspectives. However, almost none of the existing SSE schemes considers the data distribution issues. We find that when the dataset is not distributed uniformly, the search quality based on the conventional methods decreases. Therefore, the existing SSE schemes cannot guarantee high search quality when faced with non-uniform datasets. In addition, most existing SSE solutions cannot hide the distribution of the query set. In this article, we design a S\ecure similarity search over Encrypted Non-uniform and high-dimensional Datasets (SEND) with a novel way to enhance security. The basic idea is to combine SSE with locality-sensitive hashing (LSH). Unlike earlier schemes, SEND uses selective hashing, which has better performance for non-uniform datasets. Also, we present a novel approach to hide the distribution of the query set, which makes SEND more secure. Our experimental results indicate SEND achieves a high search quality of recall and precision, and it is proven secure against adaptively chosen query attacks in the standard model.

With the emergence of intelligent terminals, the Content-Based Image Retrieval (CBIR) technique has attracted much attention from many areas (i.e., cloud computing, social networking services, etc.). Although existing privacy-preserving CBIR schemes can guarantee image privacy while supporting image retrieval, these schemes still have inherent defects (i.e., low search accuracy, low search efficiency, key leakage, etc.). To address these challenging issues, in this article we provide a similarity Search for Encrypted Images in secure cloud computing (called SEI). First, the feature descriptors extracted by the Convolutional Neural Network (CNN) model are used to improve search accuracy. Next, an encrypted hierarchical index tree by using$K$-means clustering based on Affinity Propagation (AP) clustering is devised, which can improve search efficiency. Then, a limited key-leakage k-Nearest Neighbor (kNN) algorithm is proposed to protect key from being completely leaked to untrusted image users. Finally, SEI is extended to further prevent image users’ search information from being exposed to the cloud server. Our formal security analysis proves that SEI can protect image privacy as well as key privacy. Our empirical experiments using a real-world dataset illustrate the higher search accuracy and efficiency of SEI.

With the advent of cloud computing, explosively increasing images are gradually outsourced to the cloud server for costs saving and feasibility. For security and privacy concerns, images (e.g., medical diagnosis, personal photos) should be encrypted before being outsourced. However, traditional encrypted image retrieval techniques still suffer from costly access control and low search accuracy. To solve these challenging issues, in this article, we first propose a Controllable encrypted cloud image Search scheme in Multi-user settings (namely CSM) by using the polynomial-based access strategy and proxy re-encryption technique. CSM achieves efficient access control and avoids heavy communication overhead caused by key transmission. Then, we improve the basic CSM to achieve malicious search user Tracing (namely TCSM) by utilizing the watermark technique, which can further prevent search users from illegally redistributing retrieved images to unauthorized search users. Our formal security analysis proves that our CSM (or TCSM) can guarantee the privacy of images, indexes, and search queries. Our empirical experiments using real-world datasets demonstrate the efficiency and high accuracy of our CSM (or TCSM) in practice.

With the explosive growth of data volume in the cloud computing environment, data owners are increasingly inclined to store their data on the cloud. Although data outsourcing reduces computation and storage costs for them, it inevitably brings new security and privacy concerns, as the data owners lose direct control of sensitive data. Meanwhile, most of the existing ranked keyword search schemes mainly focus on enriching search efficiency or functionality, but lack of providing efficient access control and formal security analysis simultaneously. To address these limitations, in this article we propose an efficient and privacy-preservingMulti-keywordRankedSearch scheme withFine-grained access control (MRSF). MRSF can realize highly accurate ciphertext retrieval by combining coordinate matching with Term Frequency-Inverse Document Frequency (TF-IDF) and improving the secure$k$NN method. Besides, it can effectively refine users’ search privileges by utilizing the polynomial-based access strategy. Formal security analysis shows that MRSF is secure in terms of confidentiality of outsourced data and the privacy of index and tokens. Extensive experiments further show that, compared with existing schemes, MRSF achieves higher search accuracy and more functionalities efficiently.

Searchable Encryption (SE) is a popular cryptographic primitive for building ciphertexts retrieval systems with far-reaching applications. However, existing SE schemes generally do not support threshold access control (i.e., data users must collaboratively issue search and decryption operations over encrypted cloud data) in a group-oriented cloud data sharing setting, which is increasingly receiving much attention in the research community. Thus, in this article, we first propose a Threshold Multi-keyword Search (TMS) scheme for cloud-based group data sharing (referred to as basic TMS scheme) by utilizing Shamir’s secret sharing technique, to achieve threshold multi-keyword search, threshold decryption, and short record ciphertext size. Then, we extend this basic TMS to realize threshold result verification and threshold traceability (referred to as enhanced TMS). Furthermore, the enhanced TMS is extended to support public result verification and dynamic operations with the public verifier and improved hash tables, respectively. Our formal security analysis proves that both basic TMS and enhanced TMS are semi-adaptively secure and can resist Chosen-Keyword Attack (CKA). Our theoretical evaluation and empirical experiments demonstrate the potential utility of both schemes.

Searchable encryption (SE) allows cloud tenants to retrieve encrypted data while preserving data confidentiality securely. Many SE solutions have been designed to improve efficiency and security, but most of them are still susceptible to insider Keyword-Guessing Attacks (KGA), which implies that the internal attackers can guess the candidate keywords successfully in an off-line manner. Also in existing SE solutions, a semi-honest-but-curious cloud server may deliver incorrect search results by performing only a fraction of retrieval operations honestly (e.g., to save storage space). To address these two challenging issues, we first construct the basic Verifiable SE Framework (VSEF), which can withstand the inside KGA and achieve verifiable searchability. Based on the basic VSEF, we then present the enhanced VSEF to support multi-keyword search, multi-key encryption and dynamic updates (e.g., data modification, data insertion, and data deletion) at the same time, which highlights the importance of practicability and scalability of SE in real-world application scenarios. We conduct extensive experiments using the Enron email dataset to demonstrate that the enhanced VSEF achieves high efficiency while resisting to the inside KGA and supporting the verifiability of search results.

Cloud-assisted Internet of Things (IoT) is increasingly prevalent used in various fields, such as the healthcare system. While in such a scenario, sensitive data (e.g., personal electronic medical records) can be easily revealed, which incurs potential security challenges. Thus, Symmetric Searchable Encryption (SSE) has been extensively studied due to its capability of supporting efficient search on encrypted data. However, most SSE schemes require the data owner to share the complete key with query users and take malicious cloud servers out of consideration. Seeking to address these limitations, in this article we propose a Verifiable Privacy-preserving data Search scheme with Limited key-disclosure (VPSL) for cloud-assisted Internet of Things. VPSL first designs a trapdoor generation protocol for obtaining a trapdoor with disclosing limited key information and without revealing plaintext query points to others. Then, VPSL provides an efficient result verification and search processing by employing the Merkle hash tree structure and k-means clustering technique, respectively. VPSL is secure against the level-2 attack. Finally, an enhanced VPSL (called VPSL+) resisting the level-3 attack is constructed by introducing the random splitting technique. Empirical experiments demonstrate the accuracy and efficiency of VPSL or VPSL+ using real-world datasets.

Healthcare Internet-of-Things (IoT) is an emerging paradigm that enables embedded devices to monitor patients vital signals and allows these data to be aggregated and outsourced to the cloud. The cloud enables authorized users to store and share data to enjoy on-demand services. Nevertheless, it also causes many security concerns because of the untrusted network environment, dishonest cloud service providers and resource-limited devices. To preserve patients’ privacy, existing solutions usually apply cryptographic tools to offer access controls. However, fine-grained access control among authorized users is still a challenge, especially for lightweight and resource-limited end-devices. In this paper, we propose a novel healthcare IoT system fusing advantages of attribute-based encryption, cloud and edge computing, which provides an efficient, flexible, secure fine-grained access control mechanism with data verification in healthcare IoT network without any secure channel and enables data users to enjoy the lightweight decryption. We also define the formal security models and present security proofs for our proposed scheme. The extensive comparison and experimental simulation demonstrate that our scheme has better performance than existing solutions.

In this article, we propose a privacy-preserving medical treatment system using nondeterministic finite automata (NFA), hereafter referred to as P-Med, designed for remote medical environment. P-Med makes use of the nondeterministic transition characteristic of NFA to flexibly represent medical model, which includes illness states, treatment methods and state transitions caused by exerting different treatment methods. A medical model is encrypted and outsourced to cloud to deliver telemedicine service. Using P-Med, patient-centric diagnosis and treatment can be made on-the-fly while protecting the confidentiality of patient’s illness states and treatment recommendation results. Moreover, a new privacy-preserving NFA evaluation method is given in P-Med to get a confidential match result for the evaluation of an encrypted NFA and an encrypted data set, which avoids the cumbersome inner state transition determination. We demonstrate that P-Med realizes treatment procedure recommendation without privacy leakage to unauthorized parties. We conduct extensive experiments and analysis to evaluate the efficiency.

Blockchain allows for secure management of a shared ledger by agreement protocols, where transactions are validated over network without central authorities. Although the agreement protocol has been thoroughly conducted of propagation and consensus researches, mobility of nodes in unstructured overlay networks has not received much attention. Besides, current dynamic propagation schemes waste travel hops and are low of delivery ratio. In this article, we propose a social characteristic-based propagation-efficient protocol NefSBFT to agree on system state plus consensus mechanisms in public blockchains. We devise a propagation technique (travel hops of at least$\frac{1}{3}$savings, delivery ratio above 0.93, etc.) for message multicasting when exploiting real nodes’ social characteristics of intermittent connectivity and frequent partitions. This propagation technique is executed in the improved FastBFT to achieve transaction ordering and block verification, thus, no controllable mobility is required during the whole system’s execution. NefSBFT achieves fast propagation, small message complexity and few resource consumption of travel hops and running nodes for complete protocol execution. We analyze NefSBFT’s security against DDOS attack of non-primary failure. The experiments show the performance tradeoff under different parameters, compare the propagation efficiency with Erlay and Flooding, and clarify NefSBFT’s impact on the whole system performance through comparison.

Random forest is one of the most heated machine learning tools in a wide range of industrial scenarios. Recently, federated learning enables efficient distributed machine learning without direct revealing of private participant data. In this article, we present a novel framework of federated random forest (RevFRF), and further emphatically discuss the participant revocation problem of federated learning based on RevFRF. Specifically, RevFRF first introduces a suite of homomorphic encryption based secure protocols to implement federated random forest (RF). The protocols cover the whole lifecycle of an RF model, including construction, prediction and participant revocation. Then, referring to the practical application scenarios of RevFRF, the existing federated learning frameworks ignore a fact that even every participant in federated learning cannot maintain the cooperation with others forever. In company-level cooperation, allowing the remaining companies to use a trained model that contains the memories from an off-lying company potentially leads to a significant conflict of interest. Therefore, we propose the revocable federated learning concept and illustrate how RevFRF implements participant revocation in applications. Through theoretical analysis and experiments, we show that the protocols can efficiently implement federated RF and ensure the memories of a revoked participant in the trained RF to be securely removed.

Cloud-based data storage service has drawn increasing interests from both academic and industry in the recent years due to its efficient and low cost management. Since it provides services in an open network, it is urgent for service providers to make use of secure data storage and sharing mechanism to ensure data confidentiality and service user privacy. To protect sensitive data from being compromised, the most widely used method is encryption. However, simply encrypting data (e.g., via AES) cannot fully address the practical need of data management. Besides, an effective access control over download request also needs to be considered so that Economic Denial of Sustainability (EDoS) attacks cannot be launched to hinder users from enjoying service. In this article, we consider thedual access control, in the context of cloud-based storage, in the sense that we design a control mechanism over both data access and download request without loss of security and efficiency. Two dual access control systems are designed in this article, where each of them is for a distinct designed setting. The security and experimental analysis for the systems are also presented.

In the era of cloud computing, to achieve convenient location-based service (LBS), consumers such as users, companies, and organizations prefer subcontracting massive geographical data to public clouds after encryption for privacy and security. However, numerous harmful cyber-attacks happen on those public clouds in an unpredicted and hourly manner. To alleviate those concerns, various secure query schemes on the encrypted data have been proposed in the literature. As a fundamental query of LBSs, forward-secure range query has not been well investigated. To address this issue, we propose a lightweight and forward-secure range query (LS-RQ) on geographically encrypted data, which soundly balances between security and efficiency. Promisingly, we design an index mechanism to manage geographical data on the public clouds, while not compromising the privacy of data. Moreover, our LS-RQ schemes provide a convenient approach to range query on geographically encrypted data on-the-fly. We also rigorously prove that LS-RQ is forward-secure. Finally, extensive experimental studies are performed on both real and synthetic datasets. By observation, our LS-RQ schemes are highly efficient in realistic environments. Particularly, on encrypted datasets with about 1000000 geographical data, our solution to secure range query takes strictly less than a second.

Cloud attack provenance is a well-established industrial practice for assuring transparency and accountability for a service provider to tenants. However, the multi-tenancy and self-service nature coupled with the sheer size of a cloud implies many unique challenges to cloud forensics. Although Virtual Machine Introspection (VMI) is a powerful tool for attack provenance due to the privilege isolation, the stealthiness of state-of-the-art attacks and the lack of precise information make existing attack provenance solutions difficult to fulfill real-time forensics when tracking enormous suspicious behaviors. To this end, we propose an instruction-level tracing framework for inspecting the presence of attacks by dynamically tracking shared processor hardware event patterns and analyzing the attack traces. To overcome the challenges of real-time detection and provenance, we advocate Last Branch Record (LBR) profiling, to extract the suspicious execution flows. With the hardware assistance and software-based virtualization introspection, we show that the framework can provide an effective response to threats in different cases, thereby enabling a quick attack provenance with high fidelity. The evaluation shows that our prototype introduces negligible performance penalties.

In this paper, we propose a lightweight privacy-preserving Faster R-CNN framework (SecRCNN) for object detection in medical images. Faster R-CNN is one of the most outstanding deep learning models for object detection. Using SecRCNN, healthcare centers can efficiently complete privacy-preserving computations of Faster R-CNN via the additive secret sharing technique and edge computing. To implement SecRCNN, we design a series of interactive protocols to perform the three stages of Faster R-CNN, namely feature map extraction, region proposal and regression and classification. To improve the efficiency of SecRCNN, we improve the existing secure computation sub-protocols involved in SecRCNN, including division, exponentiation and logarithm. The newly proposed sub-protocols can dramatically reduce the number of messages exchanged during the iterative approximation process based on the coordinate rotation digital computer algorithm. Moreover, the effectiveness, efficiency and security of SecRCNN are demonstrated through comprehensive theoretical analysis and extensive experiments. The experimental findings show that the communication overhead in computing division, logarithm and exponentiation decreases to 36.19%, 73.82% and 43.37%, respectively.

Internet purification is a necessary technique to defend against Distributed Denial-of-Service (DDoS) attack. It can help Internet Service Provider (ISP) to completely and precisely scrub attack traffic through establishing the sender-receiver pair based filtering rules in networks. However, when faced with the Link Flooding Attacks (LFA), a new kind of DDoS, existing relevant schemes suffer the drawbacks, including the weak willingness of defense cooperation between Autonomous Systems (ASes), lower filtering efficiency and poor robustness. For this, we propose STOP, a service-oriented Internet purification technique designed to defend against LFA. In STOP, malicious traffic filtering is viewed as a value-added service and each filter contributor (i.e., AS) can get some benefit from it. This helps ASes to strengthen the willing of defense cooperation. Moreover, we devise a filter recommendation algorithm to maximize the filtering efficiency, with minimum service cost and bandwidth damages. Furthermore, in the face of the strategic threats that aim to paralyze or bypass STOP, we devise relevant defense techniques to make it more robust. Through rigorous mathematical analysis and extensive experiments based on real-world topology, we demonstrate that compared with prior work, STOP increases the filtering efficiency by 12%.

Mobile crowdsensing has emerged as a popular platform to solve many challenging problems by utilizing users’ wisdom and resources. Due to user diversity, the data provided by different individuals may vary significantly, and thus it is important to analyze data quality during data aggregation. Truth discovery is effective in capturing data quality and obtaining accurate mobile crowdsensing results. Existing works on truth discovery either cannot protect both task privacy and data privacy, or introduce tremendous computational costs. In this paper, we propose an efficient and strong privacy-preserving truth discovery scheme, named EPTD, to protect users’ task privacy and data privacy simultaneously in the truth discovery procedure. In EPTD, we first exploit the randomizable matrix to express users’ tasks and sensory data. Then, based on the matrix computation properties, we design key derivation and (re-)encryption mechanisms to enable truth discovery to be performed in an efficient and privacy-preserving manner. Through a detailed security analysis, we demonstrate that data privacy and task privacy are well preserved. Extensive experiments based on real-world and simulated mobile crowdsensing applications show EPTD has practical efficiency in terms of computational cost and communication overhead.

Secure outsourced computation is a key technique for protecting data security and privacy in the cloud. Although fully homomorphic encryption (FHE) enables computations over encrypted data, it suffers from high computation costs in order to support an unlimited number of arithmetic operations. Recently, secure computations based on interactions of multiple computation servers and partially homomorphic encryption (PHE) were proposed in the literature, which enable an unbound number of addition and multiplication operations on encrypted data more efficiently than FHE and do not add any noise to encrypted data; however, these existing solutions are either limited in functionalities (e.g., computation on natural numbers only) or leak information of the underlying data. To tackle these shortcomings, this paper proposes Secure Outsourced Computation on Integers (SOCI) based on PHE and a twin-server architecture. Compared with the existing solutions, SOCI supports computations on encrypted integers (vs. natural numbers) and greatly improves the security and correctness of the computations. Results of theoretical analysis and experimental evaluation show that SOCI outperforms existing solutions in computation and communication efficiencies.

Due to resource constraints and working surroundings, many IIoT nodes are easily hacked and turn into zombies from which to launch attacks. It is challenging to detect such networked zombies rooted behind the Internet for any individual defender. In this article, we combine federated learning (FL) and fog/edge computing to combat malicious codes. Our protocol trains a global optimized model based on distributed datasets of collaborators while removing the data and communication constraints. The FL-based detection protocol maximizes the values of distributed data samples, resulting in an accurate model timely. On top of the protocol, we place mitigation intelligence in a distributed and collaborative manner. Our approach improves accuracy, eliminates mitigation time, and enlarges attackers’ expense within a defense alliance. Comprehensive evaluations confirm that the cost incurred is 2.7 times larger, the mitigation response time is 72% lower, and the accuracy is 47% higher on average. Besides, the protocol evaluation shows the detection accuracy is approximately 98% in the FL, which is almost the same as centralized training.

As a novel network infrastructure that realizes the interconnection of humans, machines, and things, 5G enables a large number of devices with communication and sensing capabilities to securely, quickly, and reliably connect to the Internet and facilitates Industrial Internet of Things (IIoT) applications such as smart cities, smart homes, and smart grids. The 5G technique has potential applications in various military and civilian settings such as radar anomaly detection, unmanned aerial vehicles (UAV) data storage sharing [A1], [A2], and traffic data analysis.

With the large-scaled data generated from various interconnected machines and networks, Industrial Internet of Things (IIoT) provides unprecedented opportunities for facilitating data mining for industrial applications. The current IIoT architecture tends to adopt cloud computing for further timely mining IIoT data, however, the openness of security-critical IIoT becomes challenging in terms of unbearable privacy issues. Most existing privacy-preserving data mining (PPDM) techniques are designed to resist honest-but-curious adversaries (i.e., cloud servers and data users). Due to the complexity and openness in IIoT, PPDM is significantly difficult with the presence of malicious adversaries in IIoT who may incur incorrect learned models and inference results. To solve the aforementioned issues, we propose a framework to extend existing PPDM to guard linear regression against malicious behaviors (hereafter referred to as GuardLR). To prevent dishonest computations of cloud servers and inconsistent inputs of data users, we first design a privacy-preserving verifiable learning scheme for linear regression, which guarantees the correctness of learning. In this article, to avoid malicious clouds from returning incorrect inference results, we design a privacy-preserving prediction scheme with lightweight verification. Our formal security analysis shows that GuardLR achieves privacy, completeness, and soundness. Empirical experiments using real-world datasets also demonstrate that GuardLR has high computational efficiency and accuracy.

Due to the safe portability of the device in sixth generation (6G) enabled network in box (NIB) and the mobility of locations, users equipped with the device can have a better experience in spatial crowdsourcing. The integration of NIB with 6G results in a decentralized spatial crowdsourcing in industrial automation, but threatens the security of tasks and answers and also leads to the leakage of sensing nodes’ locations. To address these problems, in this article, we propose a secure decentralized spatial crowdsourcing scheme for 6G-enabled NIB (DSC-NIB). Using DSC-NIB, the control station and sensing nodes can gather and transmit information on the blockchain using NIB, without depending on the third party. The control station shares encrypted location strategy parameters set to negotiate session keys and a group key with sensing nodes whose locations satisfy the location strategy, while ensuring the privacy of sensing nodes’ locations. For the security of tasks and answers, we leverage the Counter with CBC-MAC authenticated encryption mechanism to provide confidentiality and integrity. Furthermore, we analyze the security of the proposed DSC-NIB. Compared with existing approaches, the performance is evaluated and improved by 30--50%. To further optimize the performance, two optimized schemes without sacrificing security are presented and our results demonstrate that performance is improved greatly.

With the assistance of the Internet of Things, the fast developing Healthcare Internet of Things (H-IoT) has promoted the healthcare ecosystem into the era of Health 5.0 and enables many promising medical applications, such as remote healthcare that is crucial in pandemic (e.g., coronavirus disease 2019). Healthcare participants can make accurate diagnosis, treatment, and research based on the shared personal health records (PHRs) sensed from remote H-IoT devices. However, current H-IoT systems fall short of a secure and trustworthy PHR sharing service in remote healthcare, which is able to prevent user privacy leakage and PHR integrity violation together with high efficiency in key distribution alongside efficient data retrieval and fine-grained access control. In response, we present a blockchain-based hierarchical data sharing framework (BHDSF) to provide fine-grained access control and efficient retrieval over encrypted PHRs with low consumed hierarchical key distribution and key leakage resistance. Compared with the existing solutions, the BHDSF takes both untrusted cloud and malicious auditor into consideration simultaneously and achieves trustworthy PHR integrity auditing and metadata verification by leveraging the blockchain technique. Besides, the BHDSF enables efficiently aggregative authentication for the trustworthiness of source records from H-IoT devices, which is lacked in most of the existing data sharing frameworks. Finally, we demonstrate the feasibility of the BHDSF by conducting extensive empirical tests over a real-world dataset.

Connected autonomous vehicles (CAVs) employ the point cloud data captured by LiDAR to enhance the capability of object recognition and detection. Edge computing with its inherent advantages can help CAVs alleviate resource constraints and enable faster situational awareness and data processing. However, the point cloud data contains private information, such as vehicle identity, location and trajectory, directly uploading the raw point cloud to the edge nodes or other vehicle will lead to serious privacy leakage. To the best of our knowledge, we are the first to try to tackle this challenge and propose a privacy-preserving object detection framework over random point cloud shares for CAVs (referred to SecPCV), aiming to guarantee the privacy of both point cloud and object detection results. In SecPCV, CAVs split point cloud into two random shares based on additive secret sharing (ASS) and upload them to two competing edge nodes, respectively, which greatly compress the computational load of CAVs. Without changing the object detection network in plaintext environment, the edge nodes can cooperatively and securely extract, regress, and classify over point cloud shares. Theoretical analysis ensure the efficiency and security of the SecPCV framework. Experimental results with the real KITTI point cloud dataset indicate that SecPCV can achieve the consistent object detection accuracy as that in plaintext environment, and provide a feasible solution for CAVs secure sharing of point cloud data.

Location-based routing is a widely adopted message transmission mechanism in Vehicular Ad Hoc Networks (VANETs). While the existing location-based routing schemes of VANETs ignore the location privacy protection of vehicles, leading that the drivers to be tracked, and further threaten the safety of their life and property. To address the above issue, we propose an All-Round and Highly Privacy-Preserving Location-Based Routing for VANETs (called ARPLR). Specifically, ARPLR first proposes a road side unit assisted location management with location privacy protection that prevents the destination vehicle’s location from being leaked by the arbitrary query. Then, a message routing based on location ciphertext with highly privacy protection is designed by order revealing encryption, in which a multi-hop routing between the source and destination vehicle is established only by comparing the encrypted locations between intermediate vehicles. Security analysis shows that, ARPLR can not only effectively provide location privacy protection for the intermediate and the destination vehicles in the whole routing process, but also ensure end-to-end secure communication between the source and destination vehicles. Extensive experiments based on real-road map indicate that, compared with two state-of-the-art solutions, the average transmission delay of ARPLR is respectively reduced by about 18% and 60%, meanwhile the average packet delivery rate also increases about 30% and 2%, respectively.

A new trend of using deep reinforcement learning for traffic signal control has become a spotlight in the Intelligent Transportation System (ITS). However, the traditional intelligent traffic signal control system always collects and transmits vehicle information (e.g., vehicle location, speed, etc.) in the form of plaintext, which would result in the leakage of commuters’ privacy and thus bring unnecessary troubles to users. In this paper, we propose a privacy-preserving traffic signal control for an intelligent transportation system (PrivacySignal). It relies on the existing road facilities to achieve the privacy of commuters, which guarantees the practicality of the system. Real-time decision-making and confidentiality of the system can be achieved simultaneously via the design of a series of secure and efficient interactive protocols, that are based on additive secret sharing, to perform the deep$Q$-network (DQN). Moreover, the security of PrivacySignal is testified, meanwhile, the system effectiveness, and the overall efficiency of PrivacySignal is demonstrated through theoretical analysis and simulation experiments. Compared with the existing privacy-preserving schemes of the intelligent traffic signal, PrivacySignal provides a general DQN based privacy-preserving traffic signal control strategy architecture with high efficiency and low-performance loss.

To obtain reliable results from conflicting data in mobile crowdsensing, numerous truth discovery protocols have been proposed in the past decade. However, most of them do not consider the data privacy of entities involved (e.g., workers and servers), and several existing privacy-preserving truth discovery protocols either provide limited privacy protection or have heavy computation and communication overheads due to iterative computation and transmission over large ciphertexts. In this paper, we aim to propose privacy-preserving and lightweight truth discovery protocols to tackle the above problems. Specifically, we carefully design an anonymization protocol named AnonymTD to delink workers from their data, where workers’ data are computed and transmitted without complicated encryption. To further reduce each worker's overheads in the scenarios where workers are willing to share their weights, we resort to the perturbation technology to propose a more lightweight truth discovery protocol named PerturbTD. Based on workers’ perturbed data, two cloud servers in PerturbTD complete most of the workload of truth discovery together, which avoids the frequent involvement of workers. The theoretical analysis and the comparative experiments in this paper demonstrate that our two protocols can achieve our security goals with low computation and communication overheads.

A set of$k$spanning trees in a graph$G$are called completely independent spanning trees (CISTs for short) if the paths joining every pair of vertices$x$and$y$in any two trees have neither vertex nor edge in common, except for$x$and$y$. The existence of multiple CISTs in the underlying graph of a network has applications in fault-tolerant broadcasting and secure message distribution. In this paper, we investigate the construction of CISTs in a server-centric data center network called BCube connected crossbars (BCCC), which can provide good network performance using inexpensive commodity off-the-shelf switches and commodity servers with only two network interface card (NIC) ports. The significant advantages of BCCC are its good expandability, lower communication latency, and higher robustness in component failure. Based on the structure of compound graphs of BCCC, we provide efficient algorithms to construct$\lceil \frac{n}{4}\rceil$CISTs in the logical graph of BCCC, denoted by$L$-$BCCC(n,k)$, for$n\geqslant 5$. As a by-product, we obtain a fault-tolerant routing that takes the constructed CISTs as its routing table. We then evaluate the performance of the fault-tolerant routing through simulation results.

Ranked keyword search has gained Ranked keyword search has gained traction due to its attractive properties such as flexibility and accessibility. However, most existing ranked keyword search schemes ignore the semantic associations between the documents and queries. To solve this challenging issue in cloud-assisted edge computing, we first design theSemantic-awareRankedMulti-keywordSearch (SRMS) scheme by adopting the Latent Dirichlet Allocation (LDA) topic model and the Chinese Remainder Theorem (CRT)-based secret sharing mechanism. Considering that the cloud server may be malicious, we implement a basic verification mechanism in SRMS to verify the correctness and completeness of search results and extend this verification mechanism in cloud-assisted edge computing scenarios. Formal security analysis proves that SRMS and extended result verification mechanisms are secure in both the known ciphertext model and the known background model. Extensive experiments using the real-world dataset demonstrate that SRMS is efficient and practical.

Federated learning has become prevalent in medical diagnosis due to its effectiveness in training a federated model among multiple health institutions (i.e., Data Islands (DIs)). However, increasingly massive DI-level poisoning attacks have shed light on a vulnerability in federated learning, which inject poisoned data into certain DIs to corrupt the availability of the federated model. Previous works on federated learning have been inadequate in ensuring the privacy of DIs and the availability of the final federated model. In this article, we design a secure federated learning mechanism with multiple keys to prevent DI-level poisoning attacks for medical diagnosis, calledSFAP. Concretely,SFAPprovides privacy-preserving random forest-based federated learning by using the multi-key secure computation, which guarantees the confidentiality of DI-related information. Meanwhile, a secure defense strategy over encrypted locally-submitted models is proposed to resist DI-level poisoning attacks. Finally, our formal security analysis and empirical tests on a public cloud platform demonstrate the security and efficiency ofSFAPas well as its capability of resisting DI-level poisoning attacks.

With the development of machine learning, it is popular that mobile users can submit individual symptoms at any time anywhere for medical diagnosis. Edge computing is frequently adopted to reduce transmission latency for real-time diagnosis service. However, the data-driven machine learning, which requires to build a diagnosis model over vast amounts of medical data, inevitably leaks the privacy of medical data. It is necessary to provide privacy preservation. To solve above challenging issues, in this article, we design a lightweight privacy-preserving medical diagnosis mechanism on edge, called LPME. Our LPME redesigns the extreme gradient boosting (XGBoost) model based on the edge-cloud model, which adopts encrypted model parameters instead of local data to remove amounts of ciphertext computation to plaintext computation, thus realizing lightweight privacy preservation on resource-limited edge. In addition, LPME provides secure diagnosis on edge with privacy preservation for private and timely diagnosis. Our security analysis and experimental evaluation indicates the security, effectiveness, and efficiency of LPME.

To ensure the security of images outsourced to the malicious cloud without affecting searchability on such outsourced (typically encrypted) images, one could use privacy-preserving Content-Based Image Retrieval (CBIR) primitive. However, conventional privacy-preserving CBIR schemes based on Searchable Symmetric Encryption (SSE) are not capable of supporting efficient fine-grained access control and result verification simultaneously. Therefore, in this article, we propose aVerifiableFine-grained encryptedImageRetrieval scheme in theMulti-owner multi-user settings (VFIRM). VFIRM first utilizes a novel polynomial-based access strategy to provide efficient fine-grained access control. Then, it employs the dual secure$k$-nearest neighbor technique to distribute distinct keys to different data owners and data users, and finally implements an adapted homomorphic MAC technique to check the correctness of search results. Our formal security analysis shows that VFIRM is non-adaptive semantic secure if the client's search key is generated randomly and keeps in secret. Our empirical experiments using two real-world datasets (i.e., Caltech101 and Corel5k) demonstrate the practicality of VFIRM.

With the development of Mobile Healthcare Monitoring Network (MHMN), patients’ data collected by body sensors not only allows patients to monitor their health or make online pre-diagnosis but also enables clinicians to make proper decisions by utilizing data mining technique. However, sensitive data privacy is still a major concern. In this article, we propose practical techniques for searching and making online pre-diagnosis over encrypted data. First, we propose a new Diverse Keyword Searchable Encryption (DKSE) scheme which supports multi-dimension digital vectors range query and textual multi-keyword ranked search to gain a broad range of applications in practice. In addition, a framework called PRIDO based on the DKSE is designed to protect patients’ personal data in data mining and online pre-diagnosis. According to the PRIDO framework, we achieve privacy-preserving naïve Bayesian and decision tree classifiers and discuss its potential applications in actual deployments. Security analysis proves that patients’ data privacy can be well protected without loss of data confidentiality, and performance evaluation demonstrates the efficiency and accuracy in the diverse keyword search, data mining, and disease pre-diagnosis, respectively.

Ciphertext-Policy Attribute-Based Encryption (CP-ABE) is one of the potent encryption paradigms in protecting data confidentiality in the cloud data sharing scenario. However, the access policy of the traditional CP-ABE is in plaintext form that reveals significant sensitive information of data owners and data visitors. To mitigate this problem, two approaches have been proposed in the literature. One is partially hidden, where the attributes in the access policy are divided into two parts: the plaintext attribute names and the hidden attribute values. The other approach fully hides the attributes in the access policy which, unfortunately, hinders efficient and correct decryption as well as dynamic policy-updating. In this article, we design a security-enhanced Attribute Cuckoo Filter (se-ACF) to hide the access policy and propose a new CP-ABE system, called Privacy-Preserving Policy Updating ABE (3PU-ABE), which effectively integrates policy hiding and policy updating. We conduct rigorous security analysis and performance evaluation of 3PU-ABE. The results indicate that 3PU-ABE completely hides the access policy without affecting the decryption, and entails better policy-updating efficiency than similar works.

Vehicle platoon, a novel vehicle driving paradigm that organizes a group of vehicles in the nose-to-tail structure, has been considered as a potential solution to reduce traffic congestion and increase travel comfort. In such a platoon system, head vehicles’ performances are usually evaluated by user vehicles’ feedbacks. Selection of an appropriate and reliable head vehicle while not disclosing user vehicles’ privacy has become an interesting problem. In this article, we present a trust-based and privacy-preserving platoon recommendation scheme, called TPPR, to enable potential user vehicles to avoid selecting the malicious head vehicles. The basic concept of TPPR is that each user vehicle holds a trust value, and the reputation score of the head vehicle is calculated via a truth discovery process. To preserve vehicles’ privacy, pseudonyms and Paillier cryptosystem are applied. In addition, novel authentication protocols are designed to ensure that only the valid vehicles (i.e., the vehicles holding the truthful trust values and joining the vehicle platoon) can pass the authentication. A comprehensive security analysis is conducted to prove that the proposed TPPR scheme is secure against several sophisticated attacks in vehicular ad hoc networks. Moreover, extensive simulations are conducted to demonstrate the correctness and effectiveness of the proposed scheme.

As the next generation of digital microfluidic biochips (DMFBs) platform, Micro-electrode-dot-array (MEDA) has sea-of-micro-electrodes that support fine-grained control of the droplet and constant real-time monitoring of droplet paths. As MEDA biochips are expected to be had a booming market in the near future, their security, especially the protection of intellectual property (IP), has become the focus of the academic community. In this paper, we first propose a logic encryption-based IP protection scheme for MEDA biochips, called MEDASec, which is without modifying the structure. Our scheme aims to hide the droplet mix-split operation in bioassay, making the IP akin to a black-box in the manufacturing process. Besides, increasing computing power has facilitated the threat of brute force attacks on the secret key. In response to the brute force attack, we propose security metrics for the first time, called RRA, to evaluate the ratio of reagents that result from biochemical reactions. Experimental results on multiple bioassays demonstrate the effectiveness of the proposed logical encryption strategy against the brute force attack.

Recently, spatial keyword query services have been widely deployed in real-life applications, such as location-based services and social networking. Several privacypreserving spatial keyword queries solutions were proposed to guarantee data security and query privacy on outsourced data. However, those solutions are either based on broken cryptographic tools or support a single query type, and hence cannot meet the security and functionality requirements in practical applications. In this paper, we propose a Secure Spatial Keyword Queries (SSKQ) construction supporting expressive query types. Specifically, we present a secure index structure for spatial-textual data based on the encrypted Quadtree and Bloom filter, which can prune the index tree dynamically and only reveal the files associated with a set of keywords. The security analysis and the experiments conducted on real-world datasets demonstrate the security and performance of our construction.

Precision diagnosis and treatment are blending outcomes of machine learning and the Internet of Medical Things (IoMT). In the diabetes treatment, a medical center acts as a medical service provider (MSP) with patients data from IoMT devices. The MSP calculates the accurate dosage by importing the health index data into a corresponding decision-making model. However, the outsourcing unprotected patient data directly to the MSP suffers privacy leakage. In this paper, we propose a privacy-preserving optimal insulin dosing decision in the IoMT system (PIDM) to assist doctors in their decision-making with the patients privacy. To achieve practicality and confidentiality simultaneously, we design a series of secure and efficient interactive protocols depending on additive secret sharing to perform in one stage of DQN, namely, optimal decision making. Contrasted to the most relevant schemes, no additional trusted party is needed in our PIDM, which makes our system more practical and efficient. The security of PIDM is testified, meanwhile, the system effectiveness, and the overall efficiency of PIDM is demonstrated through theoretical analysis and simulation experiments.

Recent research on vision-based tasks has achieved great improvement due to the development of deep learning solutions. However, deep models have been found vulnerable to adversarial attacks where the original inputs are maliciously manipulated and cause dramatic shifts to the outputs. In this paper, we focus on adversarial attacks in image classifiers built with deep neural networks and propose a model-agnostic approach to detect adversarial inputs. We argue that the logit semantics of adversarial inputs follow a different evolution with respect to original inputs, and construct a logits-based embedding of features for effective representation learning. We train an LSTM network to further analyze the sequence of logits-based features to detect adversarial examples. Experimental results on the MNIST, CFAR-10, and CFAR-100 datasets show that our method achieves state-of-the-art accuracy for detecting adversarial examples and has strong generalizability.

In the era of machine learning, mobile users are able to submit their symptoms to doctors at any time, anywhere for personal diagnosis. It is prevalent to exploit edge computing for real-time diagnosis services in order to reduce transmission latency. Although data-driven machine learning is powerful, it inevitably compromises privacy by relying on vast amounts of medical data to build a diagnostic model. Therefore, it is necessary to protect data privacy without accessing local data. However, the blossom has also been accompanied by various problems, i.e., the limitation of training data, vulnerabilities, and privacy concern. As a solution to these above challenges, in this paper, we design a lightweight privacy-preserving medical diagnosis mechanism on edge. Our method redesigns the extreme gradient boosting (XGBoost) model based on the edge-cloud model, which adopts encrypted model parameters instead of local data to reduce amounts of ciphertext computation to plaintext computation, thus realizing lightweight privacy preservation on resource-limited edges. Additionally, the proposed scheme is able to provide a secure diagnosis on edge while maintaining privacy to ensure an accurate and timely diagnosis. The proposed system with secure computation could securely construct the XGBoost model with lightweight overhead, and efficiently provide a medical diagnosis without privacy leakage. Our security analysis and experimental evaluation indicate the security, effectiveness, and efficiency of the proposed system.

With the development of the Mobile Healthcare Monitoring Network (MHMN), patients’ data collected by body sensors not only allows patients to monitor their health or make online pre-diagnosis but also enables clinicians to make proper decisions by utilizing data mining techniques. In MHMN, patients’ personal data are collected by sensors per second and uploaded to the cloud server as multi-dimension vectors, cloud server stores the personal data as well as sends monitoring information to the hospital when the real-time data is abnormal. Hospital users (i.e., doctors, etc.) may query some samples which contain certain textual keywords or digital keywords in certain ranges for disease diagnosis or medical research. For example, a certain hospital user may query all samples with textual keywords ‘cancer; diabetes’ and digital vectors ‘age’ ∈ [30,50], ‘blood sugar’ ∈ [4,8], ‘heart rhythm’ ∈ [70,80]. Besides, the potential value of massive medical data has attracted considerable interests recently, for example, valuable results in diagnosis model can be yield with large-scale aggregation analysis of personal medical data. The cloud server can build a diagnosis model using data mining technology over massive data, so that hospital users or pre-diagnosis users upload medical data (i.e., age, blood pressure, blood sugar, etc.) to the cloud for diagnosis.

The distributed denial of service (DDoS) attack is detrimental to businesses and individuals as people are heavily relying on the Internet. Due to remarkable profits, crackers favor DDoS as cybersecurity weapons to attack a victim. Even worse, edge servers are more vulnerable. Current solutions lack adequate consideration to the expense of attackers and inter-defender collaborations. Hence, we revisit the DDoS attack and defense, clarifying the advantages and disadvantages of both parties. We further propose a joint defense framework to defeat attackers by incurring a significant increment of required bots and enlarging attack expenses. The quantitative evaluation and experimental assessment showcase that such expense can surge up to thousands of times. The skyrocket of expenses leads to heavy loss to the cracker, which prevents further attacks.

With the advancement of mobile Internet, cloud computing, and smart sensing devices, location-based services (LBSs) have become more and more indispensable in the Internet-of-Things (IoT)-based smart cities. Especially, spatial keyword queries have been widely deployed in real-life applications in recent years. Recently, several privacy-preserving spatial keyword queries schemes were proposed to guarantee data security and query privacy on outsourced data. However, these schemes support neither dynamic update nor diverse query types, which cannot meet the requirements in practical applications. This article proposes two secure dynamic spatial keyword queries (SDSKQs) constructions that support expressive query types and dynamic update. First, we present a basic SDSKQ construction based on hidden-vector encryption and order-revealing encryption. Specifically, we propose a secure hybrid index structure forspatio-textualdata, named encrypted textual signature quadtree (ETSQ-tree). Using ETSQ-tree, the server can prune the index tree according to search queries to reduce the search space. Besides, the ETSQ-tree can be updated dynamically. To resist the file-injection attack, which aims to infer query information according to newly inserted objects, we further improve the basic SDSKQ to achieve forward security. We implement our two constructions and evaluate them using real-world data sets. The experimental results show that they are efficient and feasible in practical applications, and the comparative evaluation confirms that the performance of our constructions outperforms that of the state-of-the-art schemes.

Crowdsensing is regarded as a critical component of the Internet of Things (IoT) and has been widely applied in smart city services. Incentive mechanism design, data reliability evaluation, and privacy preservation are the research focuses of crowdsensing. However, most existing incentive mechanisms fail to protect data privacy and evaluate data credibility, simultaneously. Moreover, traditional privacy and reliability-aware incentive schemes are usually challenging to realize real-time reward distribution. To this end, we first point out a single-time slice of failure problem in real-time incentive mechanisms and propose a two-layer truth discovery model (TLTD) to resolve this problem. Then, a reliability-aware real-time incentive mechanism (RRIM) is designed based on the proposed TLTD. In order to evaluate data reliability in a privacy-preserving manner, we build a privacy-preserving truth discovery solution (PriTD) based on secure computation protocols. Finally, our proposed system [privacy and reliability-aware real-time incentive system for crowdsensing (PRICE)] integrating the aforementioned protocols realizes real-time reward distribution, data reliability evaluation, and privacy protection, simultaneously. Theoretical analysis and experimental evaluations on a synthetic and real-world data set demonstrate the feasibility and efficiency of the proposed PRICE.

Dynamic Searchable Symmetric Encryption (DSSE) has gained increasing popularity as it enables users to perform both file updates and ciphertext retrieval over encrypted data . However, existing DSSE schemes still lead to privacy leakage ( e.g., forward and backward privacy) in the dynamic setting. Some forward and backward secure DSSE schemes have been proposed, but still cannot support the keyword shielding flexibly. To solve this challenging issue, we propose a Forward and Backward Authorized Keyword Search (FB-AKS) scheme with recoverable keyword shielding by using trapdoor permutations and puncturable encryption in this paper. Compared with existing forward and backward private schemes, FB-AKS achieves keyword authorization flexibly ( e.g., keyword shielding, keyword un-shielding). The formal security analysis proves that FB-AKS achieves forward and backward security. And extensive experiments demonstrate that FB-AKS has less computation and storage overheads .

Enabling remote data integrity checking with failure recovery becomes exceedingly critical in distributed cloud systems. With the properties of a lower repair bandwidth while preserving fault tolerance, regenerating coding and network coding (NC) have received much attention in the coding-based storage field. Recently, an outstanding outsourced auditing scheme named NC-Audit was proposed for regenerating-coding-based distributed storage. The scheme claimed that it can effectively achieve lightweight privacy-preserving data verification remotely for these networked distributed systems. However, our algebraic analysis shows that NC-Audit can be easily broken due to a potential defect existing in its schematic design. That is, an adversarial cloud server can forge some illegal blocks to cheat the auditor with a high probability when the coding field is large. From the perspective of algebraic security, we propose a remote data integrity checking scheme RNC-Audit by resorting to hiding partial critical information to the server without compromising system performance. Our evaluation shows that the proposed scheme has significantly lower overhead compared to the state-of-the-art schemes for distributed remote data auditing.

Person re-identification (Re-ID) has attracted extensive attention due to its potential to identify a person of interest from different surveillance videos. With the increasing amount of the surveillance videos, high computation and storage costs have posed a great challenge for the resource-constrained users. In recent years, the cloud storage services have made a large volume of video data outsourcing become possible. However, person Re-ID over outsourced surveillance videos could lead to a security threat, i.e., the privacy leakage of the innocent person in these videos. Therefore, we propose an efFicient privAcy-preseRving peRson Re-ID Scheme (FARRIS) over outsourced surveillance videos, which can ensure the privacy of the detected person while providing the person Re-ID service. Specifically, FARRIS exploits the convolutional neural network (CNN) and kernels based supervised hashing (KSH) to extract the efficient person Re-ID feature. Then, we design a secret sharing based Hamming distance computation protocol to allow cloud servers to calculate similarities among obfuscated feature indexes. Furthermore, a dual Merkle hash trees based verification is proposed, which permits users to validate the correctness of the matching results. The extensive experimental results and security analysis demonstrate that FARRIS can work efficiently, without compromising the privacy of the involved person.

The proliferation of various mobile devices equipped with cameras results in an exponential growth of the amount of images. Recent advances in the deep learning with convolutional neural networks (CNN) have made CNN feature extraction become an effective way to process these images. However, it is still a challenging task to deploy the CNN model on the mobile sensors, which are typically resource-constrained in terms of the storage space, the computing capacity, and the battery life. Although cloud computing has become a popular solution, data security and response latency are always the key issues. Therefore, in this paper, we propose a novel lightweight framework for privacy-preserving CNN feature extraction for mobile sensing based on edge computing. To get the most out of the benefits of CNN with limited physical resources on the mobile sensors, we design a series of secure interaction protocols and utilize two edge servers to collaboratively perform the CNN feature extraction. The proposed scheme allows us to significantly reduce the latency and the overhead of the end devices while preserving privacy. Through theoretical analysis and empirical experiments, we demonstrate the security, effectiveness, and efficiency of our scheme.

Ciphertext-Policy Attribute-Based Keyword Search (CP-ABKS) schemes support both fine-grained access control and keyword-based ciphertext retrieval, which make these schemes attractive for resource-constrained users (i.e., mobile or wearable devices, sensor nodes, etc.) to store, share and search encrypted data in the public cloud. However, ciphertext length and decryption overhead in the existing CP-ABKS schemes grow with the complexity of access policies or the number of data users' attributes. Moreover, such schemes generally do not consider the practical multi-owner setting (e.g., each file needs to be signed by multiple data owners before being uploaded to the cloud server) or prevent malicious cloud servers from returning incorrect search results. To overcome these limitations, in this paper we first design an optimized Verifiable Fine-grained Keyword Search scheme in the static Multi-owner setting (termed as basic VFKSM), which achieves short ciphertext length, fast ciphertext transformation, accelerated search process, and authentic search result verification. Then, we extend the basic VFKSM to support multi-keyword search and multi-owner update (also called as extended VFKSM). Finally, we prove that the basic (or extended) VFKSM resists the Chosen-Keyword Attack (CKA) and external Keyword-Guessing Attack (KGA). We also evaluate the performance of these schemes using various public datasets.

Searchable Encryption (SE) is an important technique to guarantee data security and usability in the cloud at the same time. Leveraging Ciphertext-Policy Attribute-Based Encryption (CP-ABE), the Ciphertext-Policy Attribute-Based Keyword Search (CP-ABKS) scheme can achieve keyword-based retrieval and fine-grained access control simultaneously. However, the single attribute authority in existing CP-ABKS schemes is tasked with costly user certificate verification and secret key distribution. In addition, this results in a single-point performance bottleneck in distributed cloud systems. Thus, in this paper, we present a secure Multi-authority CP-ABKS (MABKS) system to address such limitations and minimize the computation and storage burden on resource-limited devices in cloud systems. In addition, the MABKS system is extended to support malicious attribute authority tracing and attribute update. Our rigorous security analysis shows that the MABKS system is selectively secure in both selective-matrix and selective-attribute models. Our experimental results using real-world datasets demonstrate the efficiency and utility of the MABKS system in practical applications.

Ciphertext-Policy Attribute-Based Keyword Search (CP-ABKS) facilitates search queries and supports fine-grained access control over encrypted data in the cloud. However, prior CP-ABKS schemes were designed to support unshared multi-owner setting, and cannot be directly applied in the shared multi-owner setting (where each record is accredited by a fixed number of data owners), without incurring high computational and storage costs. In addition, due to privacy concerns on access policies, most existing schemes are vulnerable to off-line keyword-guessing attacks if the keyword space is of polynomial size. Furthermore, it is difficult to identify malicious users who leak the secret keys when more than one data user has the same subset of attributes. In this paper, we present a privacy-preserving CP-ABKS system with hidden access policy in Shared Multi-owner setting (basic ABKS-SM system), and demonstrate how it is improved to support malicious user tracing (modified ABKS-SM system). We then prove that the proposed ABKS-SM systems achieve selective security and resist off-line keyword-guessing attack in the generic bilinear group model. We also evaluate their performance using real-world datasets.

Task matching in crowdsourcing has been extensively explored with the increasing popularity of crowdsourcing. However, privacy of tasks and workers is usually ignored in most of exiting solutions. In this paper, we study the problem of privacy-preserving task matching for crowdsourcing with multiple requesters and multiple workers. Instead of utilizing proxy re-encryption, we propose a proxy-free task matching scheme for multi-requester/multi-worker crowdsourcing, which achieves task-worker matching over encrypted data with scalability and non-interaction. We further design two different mechanisms for worker revocation including Server-Local Revocation (SLR) and Global Revocation (GR), which realize efficient worker revocation with minimal overhead on the whole system. The proposed scheme is provably secure in the random oracle model under the Decisional q-Combined Bilinear Diffie-Hellman (q-DCDBH) assumption. Comprehensive theoretical analysis and detailed simulation results show that the proposed scheme outperforms the state-of-the-art work.

E-Healthcare systems are increasingly popular due to the introduction of wearable healthcare devices and sensors. Personal health records (PHRs) are collected by these devices and stored in a remote cloud. Due to privacy concern, these records should not be accessible by any unauthorized party, and the cloud providers should not be able to learn any information from the stored records. To address the above issues, one promising solution is to employ attribute based encryption (ABE) for fine-grained access control and searchable encryption for keyword search on encrypted data. However, most of existing ABE schemes leak the privacy of access policy which may also contain sensitive information. On the other hand, for users' devices with limited computing power and bandwidth, the mechanism should enable them to be able to search the PHRs efficiently. Unfortunately, most existing works on ABE do not support efficient keyword search on encrypted data. In this work, we propose an efficient hidden policy ABE scheme with keyword search. Our scheme enables efficient keyword search with constant computational overhead and constant storage overhead. Moreover, we enhance the recipient's privacy which hides the access policy. As of independent interest, we present a trapdoor malleability attack and demonstrate that some of previous schemes may suffer from such attack.

Anonymous Communication (AC) hides traffic patterns and protects message metadata from being leaked during message transmission. Many practical AC systems have been proposed aiming to reduce communication latency and support a large number of users. However, how to design AC systems which possess strong security property and at the same time achieve optimal performance (i.e., the lowest latency or highest horizontal scalability) has been a challenging problem. In this paper, we propose an ObliComm framework, which consists of six modular AC subroutines. We also present a strong security definition for AC, named oblivious communication, encompassing confidentiality, unobservability, and a new requirement sending-and-receiving operation hiding. The AC subroutines in ObliComm allow for modular construction of oblivious communication systems in different network topologies. All constructed systems satisfy oblivious communication definition and can be provably secure in the universal composability (UC) framework. Additionally, we model the relationship between the network topology and communication measurements by queuing theory, which enables the system's efficiency can be optimized and estimated by quantitative analysis and calculation. Through theoretical analyses and empirical experiments, we demonstrate the efficiency of our scheme and soundness of the queuing model.

Truth discovery has received considerable attention in mobile crowdsensing systems. In real practice, it is vital to resolve conflicts among a large amount of sensory data and estimate the truthful information. Although truth discovery has been widely explored to improve aggregation accuracy, numerous security and privacy issues still need to be addressed. Existing schemes either do not guarantee the privacy of each participating user, or fail to consider practical needs in crowdsensing systems. In this paper, we present two reliable and privacy-preserving truth discovery schemes for different scenarios. Our first design is fit for applications where users are relatively stable. By employing the homomorphic Paillier encryption, one-way hash chain, and super-increasing sequence techniques, this approach not only guarantees strong privacy, but also is highly efficient and practical. Our second design suits applications where users are frequently moving. In such an application, we explore data perturbation and homomorphic Paillier encryption to shift all user workloads to the server side, without compromising users' privacy. Through detailed security analysis, we demonstrate that both schemes are secure, practical, and privacy-preserving. Moreover, extensive experiments based on real world and simulated mobile crowdsensing systems, we demonstrate the efficiency of our proposed schemes.

Structured Encryption (STE), which allows a server to provide secure search services on encrypted data structures, has been widely investigated in recent years. To meet expressive search requirements in practical applications, a large number of STE constructions have been proposed either on textual keywords or spatial data. However, STE on spatio-textual data, which are widely used in location-based services, has not been fully investigated. In this paper, we formally define the notion of Spatial Keyword Structured Encryption (SKSE) and propose several concrete SKSE constructions with various efficiency-security trade-offs. Firstly, we propose a basic construction with linear search complexity, which only leaks the private files matching both spatial range query and all query keywords. Then, to improve the search efficiency on large-scale datasets, we present a novel tree-based construction with sub-linear search complexity. Finally, we introduce a post-validation approach to remove false positives and further improve storage and search performance. Our constructions are general in the sense that they can be constructed from any hidden vector encryption schemes, including public-key setting and symmetric-key setting, which can meet different sharing requirements. Our rigorous security analysis and comprehensive performance evaluation demonstrate that the proposed constructions are secure and outperform the start-of-the-art solutions.

With the development of outsourcing services, users with limited resources tend to store encrypted images on remote servers and search them anytime and anywhere. However, existing encrypted image search schemes are proposed for cloud computing scenarios, and have some defects, such as excessive bandwidth resource consumption or network delay, which are not suitable for Internet of Things (IoT) devices in edge computing environment. Therefore, we propose a secure and verifiable multikey image search (SVMIS) scheme in cloud-assisted edge computing. First, the pretrained convolutional neural network model is employed to extract image feature vectors to improve search accuracy. Then, a key distribution protocol is designed to convert the encrypted indexes of different owners, and a transformation key list is constructed to support the multikey setting in edge computing. Next, the learning with errors based secure k-nearest neighbor algorithm is used to encrypt feature vectors to improve security. Finally, the Merkle hash tree is utilized to check the correctness of search results returned by edge servers. Theoretical analysis and extensive experiments using a real-world dataset evaluate the security and effectiveness of SVMIS.

With the rapid development of Internet of Vehicles (IoV), vehicle-based spatial crowdsourcing (SC) applications have been proposed and widely applied to various fields. However, location privacy leakage is a serious issue in spatial crowdsourcing because workers who participate in a crowdsourcing task are required to upload their driving locations. In this paper, we propose a decentralized location privacy-preserving SC for IoV, which allows vehicle users to securely participate in SC with ensuring the task's location policy privacy and providing multi-level privacy preservation for workers' locations. Specifically, we introduce blockchain technology into SC, which can eliminate the control of vehicle user data by SC-server. We combine the additively homomorphic encryption and circle-based location verification to ensure the confidentiality of task's location policy. To achieve multi-level privacy preservation for workers' driving locations, we only reveal a grid where workers are located in. The size of the grid represents the level of privacy preservation. We leverage the order-preserving encryption and non-interactive zero-knowledge proof to prevent workers from illegally obtaining rewards by forging their driving locations. The security analysis results show that our framework can satisfy the above requirements. In addition, the experiment results demonstrate that our framework is efficient and feasible in practice.

Providing appropriate monetary rewards is an efficient way for mobile crowdsensing to motivate the participation of task participants. However, a monetary incentive mechanism is generally challenging to prevent malicious task participants and a dishonest task requester. Moreover, prior quality-aware incentive schemes are usually failed to preserve the privacy of task participants. Meanwhile, most existing privacy-preserving incentive schemes ignore the data quality of task participants. To tackle these issues, we propose a privacy-preserving and data quality-aware incentive scheme, called PACE. In particular, data quality consists of the reliability and deviation of data. Specifically, we first propose a zero-knowledge model of data reliability estimation that can protect data privacy while assessing data reliability. Then, we quantify the data quality based on the deviation between reliable data and the ground truth. Finally, we distribute monetary rewards to task participants according to their data quality. To demonstrate the effectiveness and efficiency of PACE, we evaluate it in a real-world dataset. The evaluation and analysis results show that PACE can prevent malicious behaviors of task participants and a task requester, and achieves both privacy-preserving and data quality measurement of task participants.

The minimum travel distance of task participants is one of the significant optimization objectives of privacy-preserving task assignment in mobile crowdsensing (MCS). However, when the travel distance is minimized, most of the previous schemes only focus on the task participant privacy and disregard the task requester privacy. Moreover, existing solutions usually only support the constraint of a single type, such as equality constraints or range constraints. In this paper, we propose a bilateral privacy-preserving Task Assignment mechanism for MCS (iTAM), which protects not only the task participants privacy but also the task requesters privacy and can minimize the travel distance. Furthermore, iTAM provides both equality and range constraints of task assignment by utilizing the Paillier cryptosystem. To accommodate the multiple relations between the task participants and the task, we propose the single/multiple task participants selection problems for a task requiring task participants to compete and cooperate. Experimental evaluations over synthetic and real-world data illustrate that iTAM is feasible and effective. Compared with the state-of-the-art, iTAM positively solves the optimal problem of travel distance. The complexities of iTAM are$\mathcal {O}(n)$and$\mathcal {O}(n\log n)$for a single and multiple task participants selection problems, respectively.

The guarantee of social stability comes from many aspects of life, and image information security as one of them is being subjected to various malicious attacks. As a means of information attack, image splicing forgery refers to copying some areas of an image to another image to hide the traces of the original information and leads to grave consequences. Image splicing forgery is extremely complex since the attributes of the two images subjected to the pasting and copying operations are greatly different. In order to solve the issue mentioned above, we propose a method by applying a neural learning network controlled by multiple scales (MCNL-Net) based on U-Net to identify whether an image has been tampered and to locate the tampered regions. Firstly, the learning capacity of MCNL-Net is enhanced by the combination of a residual propagation module and a residual feedback module. An ingenious strategy is designed to control the size of local receptive field in each building block of MCNL-Net. The strategy makes MCNL-Net able to achieve properties and superiorities of multi-scale structure and learn specified features. For further improving the detection performance of MCNL-Net, a block attention mechanism is proposed to control the advanced degree of the input information in each building block. In addition, a MaxBlurPool method is applied into image splicing forgery detection for the first time, preserving the shift-equivariance of a convolutional neural network. Through experiments, we demonstrate that MCNL-Net can achieve more promising results and offer stronger robustness than the state-of-the-art splicing forgery detection methods.

As cloud storage has been widely adopted in various applications, how to protect data privacy while allowing efficient data search and retrieval in a distributed environment remains a challenging research problem. Existing searchable encryption schemes are still inadequate on desired functionality and security/privacy perspectives. Specifically, supporting multi-keyword search under the multi-user setting, hiding search pattern and access pattern, and resisting keyword guessing attacks (KGA) are the most challenging tasks. In this article, we present a new searchable encryption scheme that addresses the above problems simultaneously, which makes it practical to be adopted in distributed systems. It not only enables multi-keyword search over encrypted data under a multi-writer/multi-reader setting but also guarantees the data and search pattern privacy. To prevent KGA, our scheme adopts a multi-server architecture, which accelerates search response, shares the workload, and lowers the key leakage risk by allowing only authorized servers to jointly test whether a search token matches a stored ciphertext. A novel subset decision mechanism is also designed as the core technique underlying our scheme and can be further used in applications other than keyword search. Finally, we prove the security and evaluate the computational and communication efficiency of our scheme to demonstrate its practicality.

In this paper, we propose a privacy-preserving clinical decision support system using Naïve Bayesian (NB) classifier, hereafter referred to as Peneus, designed for the outsourced cloud computing environment. Peneus allows one to use patient health information to train the NB classifier privately, which can then be used to predict a patient's (undiagnosed) disease based on his/her symptoms in a single communication round. Specifically, we design secure Single Instruction Multiple Data (SIMD) integer circuits using the fully homomorphic encryption scheme, which can greatly increase the performance compared with the original secure integer circuit. Then, we present a privacy-preserving historical Personal Health Information (PHI) aggregation protocol to allow different PHI sources to be securely aggregated without the risk of compromising the privacy of individual data owner. Also, secure NB classifier is constructed to achieve secure disease prediction in the cloud without the help of an additional non-colluding computation server. We then demonstrate that Peneus achieves the goal of patient health status monitoring without privacy leakage to unauthorized parties, as well as the utility and the efficiency of Peneus using simulations and analysis.

As a milestone in the development of outsourcing services, cloud computing enables an increasing number of individuals and enterprises to enjoy the most advanced services from outsourcing service providers. Because online payment and data security issues are involved in outsourcing services, the mutual distrust between users and service providers may severely impede the wide adoption of cloud computing. Nevertheless, most existing solutions only consider a specific type of services and rely on a trusted third-party to realize fair payment. In this paper, to realize secure and fair payment of outsourcing services in general without relying on any third-party, trusted or not, we introduce BPay, an outsourcing service fair payment framework based on blockchain in cloud computing. We first propose the system architecture, adversary model and design goals of BPay, then describe the design details. Our security and compatibility analysis indicates that BPay achieves soundness and robust fairness and it is compatible with the Bitcoin blockchain and the Ethereum blockchain. The key to the robust fairness and compatibility lies in an all-or-nothing checking-proof protocol and a top-down checking method. In addition, our experimental results show that BPay is computationally efficient. Finally, we present the applications of BPay in outsourcing services.

Nowadays, collaborative learning is becoming a new trend to address the data scarcity issue. To prevent potential privacy leakage, some privacy-preservation collaborative learning schemes have been proposed with data encryption, but cannot handle the setting of different data contribution among data nodes and avoid the huge overhead of implementing over encrypted data. In this paper, we design a flexible and secure decentralized collaborative learning to achieve the contribution over data nodes, where each data node can specialize the contribution extent for collaborative learning. Besides, we provide a MPC-friendly collaborative layer for the lightweight privacy preservation. Our security analysis and experimental results demonstrate the security and superiority of our system, respectively.

A new trend of using deep reinforcement learning for traffic light control has become a spotlight in the Intelligent Transportation System (ITS). Meanwhile, some promising accomplishments have also been made. However, the traditional intelligent traffic signal control system always collects and transmits vehicle information (e.g., vehicle location, speed, etc.) in the form of plaintext, which would result in the leakage of commuters' privacy. Privacy leaks cause unnecessary trouble for users. For example, the personal interests and health information of the commuter can be inferred based on the driving route of the vehicle, or receive harassment advertisements for surrounding services, etc. In this paper, we propose a privacy-preserving intelligent traffic light control (PTLC) system with Deep Q-network. To achieve practicality and confidentiality simultaneously, a series of secure and efficient interactive protocols is designed depending on additive secret sharing to perform the DQN. Moreover, the security of PTLC is testified, meanwhile, the system effectiveness, and the overall efficiency of PTLC is demonstrated through theoretical analysis and simulation experiments.

E-healthcare cloud remarkably facilitates patients to outsource their electronic health record (EHR) to achieve large-scale information sharing in real-time for improving the efficiency of diagnosis and treatment. Unfortunately, compared with other outsourced data, EHR contains more personal privacy, which makes it more preferred by the adversaries. Besides, in the e-healthcare cloud, there may exist malicious users who deliberately disclose their access privileges to obtain financial benefits. In this paper, we propose a fine-grained EHR sharing scheme in e-healthcare cloud with hidden policy and traceability. Specifically, we present a new black-box traitor tracing scheme based on partial policy hiding attribute-based encryption and it performs fine-grained access control on the encrypted EHR, which not only prevents privacy leakage from access policy but also effectively track malicious users who leak decryption privileges to construct a black-box. Our scheme is proved to be fully secure under the standard model. Performance analysis shows that the scheme can achieve the design goals in terms of storage and computation overhead. In the meantime, it is more efficient than the existing schemes under the composite order group.

Recent advances in resistive synaptic devices have enabled the emergence of brain-inspired smart chips. These chips can execute complex cognitive tasks in digital signal processing precisely and efficiently using an efficient neuromorphic system. The neuromorphic synapses used in such chips, however, are very sensitive to the external environment, thereby weakening their resistance to malicious modifications such as hardware Trojans and backdoors. Accordingly, in this paper, we propose HTcatcher, a security verification technique for hardware threat detection in neuromorphic computing systems, incorporating finite state machine and feature verification simultaneously, which has never been considered in prior work. Furthermore, we propose a pseudo-random matrix verifying technique for memory optimization, which can reduce the memory overhead of the multi-dimensional features in the system significantly. Experimental results confirm that the proposed method can identify the malicious modifications in the system accurately, while reducing the memory usage by 25%-50%.

Recently, Google and other 24 institutions proposed a series of open challenges towards federated learning (FL), which include application expansion and homomorphic encryption (HE). The former aims to expand the applicable machine learning models of FL. The latter focuses on who holds the secret key when applying HE to FL. For the naive HE scheme, the server is set to master the secret key. Such a setting causes a serious problem that if the server does not conduct aggregation before decryption, a chance is left for the server to access the user’s update. Inspired by the two challenges, we propose FEDXGB, a federated extreme gradient boosting (XGBoost) scheme supporting forced aggregation. FEDXGB mainly achieves the following two breakthroughs. First, FEDXGB involves a new HE based secure aggregation scheme for FL. By combining the advantages of secret sharing and homomorphic encryption, the algorithm can solve the second challenge mentioned above, and is robust to the user dropout. Then, FEDXGB extends FL to a new machine learning model by applying the secure aggregation scheme to the classification and regression tree building of XGBoost. Moreover, we conduct a comprehensive theoretical analysis and extensive experiments to evaluate the security, effectiveness, and efficiency of FEDXGB. The results indicate that FEDXGB achieves less than 1% accuracy loss compared with the original XGBoost, and can provide about 23.9% runtime and 33.3% communication reduction for HE based model update aggregation of FL.

With the increasing popularity of geo-positioning technologies and mobile Internet, spatial keyword data services have attracted growing interest from both the industrial and academic communities in recent years. Meanwhile, a massive amount of data is increasingly being outsourced to cloud in the encrypted form for enjoying the advantages of cloud computing while without compromising data privacy. Most existing works primarily focus on the privacy-preserving schemes for either spatial or keyword queries, and they cannot be directly applied to solve the spatial keyword query problem over encrypted data. In this paper, we study the challenging problem of Privacy-preserving Boolean Range Query (PBRQ) over encrypted spatial databases. In particular, we propose two novel PBRQ schemes. Firstly, we present a scheme with linear search complexity based on the space-filling curve code and Symmetric-key Hidden Vector Encryption (SHVE). Then, we use tree structures to achieve faster-than-linear search complexity. Thorough security analysis shows that data security and query privacy can be guaranteed during the query process. Experimental results using real-world datasets show that the proposed schemes are efficient and feasible for practical applications, which is at least ×70 faster than existing techniques in the literature.

Cloud-based Convolutional neural network (CNN) is a powerful tool for the healthcare center to provide health condition monitor service. Although the new service has future prospects in the medical, patient's privacy concerns arise because of the sensitivity of medical data. Prior works to address the concern have the following unresolved problems: 1) focus on data privacy but neglect to protect the privacy of the machine learning model itself; 2) introduce considerable communication costs for the CNN inference, which lowers the service quality of the cloud server. To push forward this area, we propose PE-HEALTH, a privacy-preserving health monitor framework that supports fully-encrypted CNN (both input data and model). In PE-HEALTH, the medical Internet of Things (IoT) sensor serves as the health condition data collector. For protecting patient privacy, the IoT sensor additively shares the collected data and uploads the shared data to the cloud server, which is efficient and suited to the energy-limited IoT sensor. To keep model privacy, PE-HEALTH allows the healthcare center to previously deploy, and then, use an encrypted CNN on the cloud server. During the CNN inference process, PE-HEALTH does not need the cloud servers to exchange any extra messages for operating the convolutional operation, which can greatly reduce the communication cost.

Abstract In this paper, we propose a framework for lightning-fast privacy-preserving outsourced computation framework in the cloud, which we refer to as LightCom. Using LightCom, a user can securely achieve the outsource data storage and fast, secure data processing in a single cloud server different from the existing multi-server outsourced computation model. Specifically, we first present a general secure computation framework for LightCom under the cloud server equipped with multiple Trusted Processing Units (TPUs), which face the side-channel attack. Under the LightCom, we design two specified fast processing toolkits, which allow the user to achieve the commonly-used secure integer computation and secure floating-point computation against the side-channel information leakage of TPUs, respectively. Furthermore, our LightCom can also guarantee access pattern protection during the data processing and achieve private user information retrieve after the computation. We prove that the proposed LightCom can successfully achieve the goal of single cloud outsourced data processing to avoid the extra computation server and trusted computation server, and demonstrate the utility and the efficiency of LightCom using simulations.

With the booming of Internet of Things (IoT), smart health (s-health) is becoming an emerging and attractive paradigm. It can provide an accurate prediction of various diseases and improve the quality of healthcare. Nevertheless, data security and user privacy concerns still remain issues to be addressed. As a high potential and prospective solution to secure IoT-oriented s-health applications, ciphertext policy attribute-based encryption (CP-ABE) schemes raise challenges, such as heavy overhead and attribute privacy of the end users. To resolve these drawbacks, an optimized vector transformation approach is first proposed to efficiently transform the access policy and user attribute set into respective vectors of shorter length while other approaches result in redundant and longer vectors. Our transformation approach can greatly relieve the costly overheard of key generation, encryption, and decryption phases. Then, based on the transformation approach and the offline/online computation technology, we propose a lightweight policy-hiding CP-ABE scheme for the IoT-oriented s-health application. With our proposed scheme, data users in the s-health system can perform lightweight encryption and decryption without leaking any sensitive privacy about the attributes of the user. Finally, the formal security analysis, the theoretic performance evaluation and experiment results indicate that the solution is secure and efficient.

As the largest Internet-of-Things (IoT) deployment in the world, the smart grid implements extremely reduction in the energy dissipation for the operation of the smart city. However, the electricity data produced by the smart grid contain massive sensitive information, such as dispatching instructions and bills. The data are always revealed to cloud servers in the plaintext format for the$Q$-learning-based energy strategy making, which gives the chance for the adversary to abuse the user data. Therefore, in this article, we propose a lightweight privacy-preserving$Q$-learning framework (LiPSG) for the energy management strategy making of the smart grid. Before being sent to the control center, the electricity data of each power supply region in LiPSG are first split into uniformly random secret shares. During completion of the computation task of$Q$-learning, the data are kept in the random share format all the time to avoid the data privacy disclosure. The computation feature is implemented by the newly proposed additive secret-sharing protocols. The edge computing technology is also deployed to further improve efficiency. Moreover, comprehensive theoretic analysis and experiments are given to prove the security and efficiency of LiPSG. Compared with the existing privacy-preserving schemes of the smart grid, LiPSG first provides a general$Q$-learning-based privacy-preserving power strategy making architecture with high efficiency and low-performance loss.

A reliable mobile crowdsensing (MCS) application usually relies on sufficient participants and trustworthy data. However, privacy concerns reduce participants' willingness to participate in sensing tasks. The uncertainty of participant behavior and heterogeneity of sensing devices result in the unreliability of sensing data and further bring unreliable MCS services. Hence, it is crucial to estimate the reliability of sensing data and protect privacy. Unfortunately, most existing privacy-preserving data estimation solutions are designed for single-type data. In practice, however, heterogeneous sensing data are ubiquitous in data integration tasks. To this end, we propose a privacy-preserving reliability estimation solution of heterogeneous data for MCS, called IronM, which is effective for text, number, and multimedia data (e.g., image, audio, and video). Specifically, IronM first formulates the reliability assessment of text, number, and multimedia data as equality and range constraints, and then estimates the reliability of heterogeneous data through our proposed privacy-preserving hybrid constraints assessment mechanism. Privacy analysis demonstrates that IronM can not only evaluate the reliability of heterogeneous data but also protect data confidentiality. The experimental results in real-world datasets show the effectiveness and efficiency of IronM.

In this paper, we propose a framework for privacy-preserving outsourced drug discovery in the cloud, which we refer to as POD. Specifically, POD is designed to allow the cloud to securely use multiple drug formula providers' drug formulas to train Support Vector Machine (SVM) provided by the analytical model provider. In our approach, we design secure computation protocols to allow the cloud server to perform commonly used integer and fraction computations. To securely train the SVM, we design a secure SVM parameter selection protocol to select two SVM parameters and construct a secure sequential minimal optimization protocol to privately refresh both selected SVM parameters. The trained SVM classifier can be used to determine whether a drug chemical compound is active or not in a privacy-preserving way. Lastly, we prove that the proposed POD achieves the goal of SVM training and chemical compound classification without privacy leakage to unauthorized parties, as well as demonstrating its utility and efficiency using three real-world drug datasets.

Secure search over encrypted remote data is crucial in cloud computing to guarantee the data privacy and usability. To prevent unauthorized data usage, fine-grained access control is necessary in multi-user system. However, authorized user may intentionally leak the secret key for financial benefit. Thus, tracing and revoking the malicious user who abuses secret key needs to be solved imminently. In this paper, we propose an escrow free traceable attribute based multiple keywords subset search system with verifiable outsourced decryption (EF-TAMKS-VOD). The key escrow free mechanism could effectively prevent the key generation centre (KGC) from unscrupulously searching and decrypting all encrypted files of users. Also, the decryption process only requires ultra lightweight computation, which is a desirable feature for energy-limited devices. In addition, efficient user revocation is enabled after the malicious user is figured out. Moreover, the proposed system is able to support flexible number of attributes rather than polynomial bounded. Flexible multiple keyword subset search pattern is realized, and the change of the query keywords order does not affect the search result. Security analysis indicates that EF-TAMKS-VOD is provably secure. Efficiency analysis and experimental results show that EF-TAMKS-VOD improves the efficiency and greatly reduces the computation overhead of users' terminals.

Mobile health (mHealth) has emerged as a new patient centric model which allows real-time collection of patient data via wearable sensors, aggregation and encryption of these data at mobile devices, and then uploading the encrypted data to the cloud for storage and access by healthcare staff and researchers. However, efficient and scalable sharing of encrypted data has been a very challenging problem. In this paper, we propose a Lightweight Sharable and Traceable (LiST) secure mobile health system in which patient data are encrypted end-to-end from a patient's mobile device to data users. LiST enables efficient keyword search and fine-grained access control of encrypted data, supports tracing of traitors who sell their search and access privileges for monetary gain, and allows on-demand user revocation. LiST is lightweight in the sense that it offloads most of the heavy cryptographic computations to the cloud while only lightweight operations are performed at the end user devices. We formally define the security of LiST and prove that it is secure without random oracle. We also conduct extensive experiments to access the system's performance.

In this paper, we propose a privacy-preserving outsourced calculation toolkit, Pockit, designed to allow data owners to securely outsource their data to the cloud for storage. The outsourced encrypted data can be processed by the cloud server to achieve commonly-used plaintext arithmetic operations without involving additional servers. Specifically, we design both signed and unsigned integer circuits using a fully homomorphic encryption (FHE) scheme, construct a new packing technique (hereafter referred to as integer packing), and extend the secure circuits to its packed version. This achieves significant improvements in performance compared with the original secure signed/unsigned integer circuit. The secure integer circuits can be used to construct a new data mining application, which we refer to as secure k-nearest neighbours classifier, without compromising the privacy of original data. Finally, we prove that the proposed Pockit achieves the goal of secure computation without privacy leakage to unauthorized parties, and demonstrate the utility and efficiency of Pockit.

Multi-keyword rank searchable encryption (MRSE) returns the top-k results in response to a data user's request of multi-keyword search over encrypted data, and hence provides an efficient way for preserving data privacy in cloud storage systems while without loss of data usability. Many existing MRSE systems are constructed based on an algorithm which we term as k-nearest neighbor for searchable encryption (KNN-SE). Unfortunately, KNN-SE has a number of shortcomings, which limit its practical applications. In this paper, we propose a new MRSE system which overcomes almost all the defects of the KNN-SE based MRSE systems. Specifically, our new system does not require a predefined keyword set and supports keywords in arbitrary languages, is a multi-user system which supports flexible search authorization and time-controlled revocation, and it achieves better data privacy protection since even the cloud server is not able to tell which documents are the top-k results returned to a data user. We also conduct extensive experiments to demonstrate the efficiency of the new system.

Due to the capacity of storing massive data and providing huge computing resources, cloud computing has been a desirable platform for doing machine learning. However, the issue of data privacy is far from being well solved and thus has been a general concern in the cloud-aided machine learning. In this work, we investigate the study of how to efficiently do decision tree training and evaluation in the cloud and meanwhile achieve privacy preservation. Unlike existing cloud server-assisted model training approaches, in our proposed solution, the whole training process is mostly done by the cloud service provider who owns the machine learning model. Since the cloud cannot directly divide the encrypted dataset according to the best attributes selected, we propose a new method for decision tree training without dataset splitting. Precisely, we design three methods for decision tree training with the different tradeoff between privacy and efficiency. In all of these methods, the outsourced data are not revealed to the cloud service provider. We also propose a privacy-preserving decision tree evaluation scheme where the cloud service provider learns nothing about the user's input and the classification result while the trained model is kept secret to the user who could only learn the classification result. Compared with previous decision tree evaluation work, our scheme achieves desirable privacy preservation against both the user and the cloud service provider, and also minimizes the user's computation and communication costs. Moreover, besides protecting the data confidentiality, our proposed scheme also supports off-line users and thus has good scalability. The real-world dataset-based experimental results demonstrate that our system is of desirable utility and efficiency.

With the development of Industry 4.0, the communication of smart grid has recently been taken seriously to ensure secure communication between operator and control center. However, the authentication process between them faces many challenges. Once the attacker successfully authenticated in the control center, the privacy data in the smart grid may leak and cause irreparable damage to the user. In addition, operator authentication is one of the most basic and crucial processes. Therefore, we propose theeye-movement and iris recognition based authentication (EmIr-Auth), a novel biometrics-based remote operator authentication scheme.EmIr-Authuses the recorded eye-movement trajectory and randomly selected iris image to authenticate operators, which is beneficial in that it is able to get rid of many cryptographic computations, as well as the need to minimize message exchange. Furthermore, except for a high-resolution camera, we do not require any additional biometric sensors in this scheme. Using the Burrows–Abadi–Needham logic, in this article, we demonstrate that our scheme provides secure authentication. Moreover, we analyze the attacks thatEmIr-Authcan resist by informal security analysis. Experimental results show thatEmIr-Authis efficient enough to deploy on portable devices and reduce the overhead of authentication procedure.

With the rapid digitalization of various industries, mobile crowdsensing (MCS), an intelligent data collection and processing paradigm of the industrial Internet of Things, has provided a promising opportunity to construct powerful industrial systems and provide industrial services. The existing unified privacy strategy for all sensing data results in excessive or insufficient protection and low quality of crowdsensing services (QoCS) in MCS. To tackle this issue, in this article we propose a personalized privacy protection (PERIO) framework based on game theory and data encryption. Initially, we design a personalized privacy measurement algorithm to calculate users' privacy level, which is then combined with game theory to construct a rational uploading strategy. Furthermore, we propose a privacy-preserving data aggregation scheme to ensure data confidentiality, integrity, and real-timeness. Theoretical analysis and ample simulations with real trajectory dataset indicate that the PERIO scheme is effective and makes a reasonable balance between retaining high QoCS and privacy.

Searchable encryption (SE) has been a promising technology which allows users to perform search queries over encrypted data. However, the most of existing SE schemes cannot deal with the shared records that have hierarchical structures. In this paper, we devise a basic cryptographic primitive called as attribute-based keyword search over hierarchical data (ABKS-HD) scheme by using the ciphertext-policy attribute-based encryption (CP-ABE) technique, but this basic scheme cannot satisfy all the desirable requirements of cloud systems. The facts that the single keyword search will yield many irrelevant search results and the revoked users can access the unauthorized data with the old or outdated secret keys make this basic scheme not scale well in practice. To this end, we also propose two improved schemes (ABKS-HD-I, ABKS-HD-II) for the sake of supporting multi-keyword search and user revocation, respectively. In contrast with the state-of-the-art attribute-based keyword search (ABKS) schemes, the computation overhead of our schemes almost linearly increases with the number of users' attributes rather than the number of attributes in systems. Formal security analysis proves that our schemes are secure against both chosen-plaintext attack (CPA) and chosen-keyword attack (CKA) in the random oracle model. Furthermore, empirical study using a real-world dataset shows that our schemes are feasible and efficient in practical applications.

Searchable encryption is an important technique for public cloud storage service to provide user data confidentiality protection and at the same time allow users performing keyword search over their encrypted data. Previous schemes only deal with exact or fuzzy keyword search to correct some spelling errors. In this paper, we propose a new wildcard searchable encryption system to support wildcard keyword queries which has several highly desirable features. First, our system allows multiple keywords search in which any queried keyword may contain zero, one or two wildcards, and a wildcard may appear in any position of a keyword and represent any number of symbols. Second, it supports simultaneous search on multiple data owner's data using only one trapdoor. Third, it provides flexible user authorization and revocation to effectively manage search and decryption privileges. Fourth, it is constructed based on homomorphic encryption rather than Bloom filter and hence completely eliminates the false probability caused by Bloom filter. Finally, it achieves a high level of privacy protection since matching results are unknown to the cloud server in the test phase. The proposed system is thoroughly analyzed and is proved secure. Extensive experimental results indicate that our system is efficient compared with other existing wildcard searchable encryption schemes in the public key setting.

Data privacy is becoming one of the most critical concerns in cloud computing. Several proposals based on Intel SGX such as VC3 [1] and M2R [2] have been introduced in the literature to protect data privacy during job execution in the cloud. However, a comprehensive formal proof of their security guarantees is still lacking. In this paper, we propose ObliDC, a general UC-secure SGX-based oblivious distributed computing framework. First, we model the life-cycle of a distributed computing job as data-flow graphs. Under the assumption of malicious, adaptive adversaries in the cloud, we then formally define data privacy of a distributed computing job by introducing a notion named ODC-privacy, which encompasses both semantic security (to protect data confidentiality during computation and transmission) and oblivious traffic (to prevent data leakage from traffic analysis). ObliDC is composed of four two-party protocols -- job deployment, job initialization, job execution, and results return, which allow for modular construction of concrete privacy-preserving job protocols in different distributed computing frameworks. Finally, inspired by a formal abstraction for trusted processors proposed by R. Pass et al. [3], we formally prove the security of ObliDC under the universal composability (UC) framework.

Traffic estimation is a popular approach to acquire traffic conditions in urban areas. At present, using the traffic data to realize the low-cost traffic estimation has already been widely favored. Although those data include various sensitive element, people ignore the harm caused by information leakage while the data are used. Additionally, the transmission of vehicle data also requires a very large communication bandwidth. To address those problems, we focus on the privacy-preserving vehicle data and reducing the amount of ciphertext data to achieve a city-scale traffic estimation. Meanwhile, we present a novel framework that integrates compressive sensing (CS) technology into privacy- preserving vehicle data. Furthermore, outsourcing vehicle data to the cloud is adopted to overcome the limitations of the in-vehicle sensors. In particular, we present a feasible computational scheme for traffic estimation, further improve the capacity of privacy- preserving and decrease system energy consumption. Finally, we validate the effectiveness of the scheme proposed through the real-world dataset.

Nowadays, Electronic Medical Records (EHRs) are closely linked to people's social lives. In order to ensure the convenience of medical services, many related organizations need to share EHRs across organizations to exchange information. The existing private EHR shareable schemes still contain some security issues, e.g., unreliability of cloud service provider, complex key calculation and unreliable backward security. In this paper, we propose an attribute-based access control scheme based on the smart contract (ABAC-SC). By virtue of the blockchain technique, ABAC-SC can be directly embedded into the existing private EHRs shareable system to solve existing unsafe problems. Considering the storage constraints of the blockchain, a data processing solution is designed to reduce the storage requirements of the pre-data upload process. We simulate our ABAC-SC scheme in Ethereum's test network Rinkeby, and the experimental results show the feasibility of our solution.

Personal Health Record (PHR) plays an important role in realizing the exchange and interaction of medical information as well as in managing chronic diseases. In the recent decade, plenty of researches have been carried out to resolve the secure sharing issue of PHR in the cloud via access control schemes. Attribute-based Encryption (ABE) is a promising technique, which implements access control by introducing the access policy. When ABE is used to construct access control scheme in the cloud, hiding and updating access policy have always been two research hotspots. However, all of the existing solutions only consider one of these two issues separately. How to combine policy hiding and policy updating to achieve secure and efficient access control has always been avoided. Furthermore, the practical deployments of traditional ABE in the medical environment are limited by its small attribute universe. In this paper, we propose a policy hiding and updating ABE (PHU-ABE) based on the Fast Attribute-based Encryption(FAME) to tackle these challenges. We argue the security of PHU- ABE. The experimental results demonstrate that our scheme not only protects users' privacy but also realizes efficient policy updating.

With the advances of outsourced computation, the threats of data leakage and loss of computational accuracy over rational domain are attracting increasing concerns. In this paper, we propose a framework for Privacy-preserving Data Sharing and high-accurate outsourced Computation system, referred as PDSC. PDSC system can perform secure data sharing with multiple data providers. Besides, the original data and computed results in the rational field can be securely processed and stored in the cloud without privacy leakage. Specifically, we design privacy-preserving computation protocols over rational numbers to guarantee computational accuracy and handle outsourced operations on-the-fly. Detailed security analysis and experimental results demonstrate that PDSC system is secure and feasible, respectively.

The traditional privacy-preserving image retrieval schemes not only bring large computational and communication overhead but also cannot well protect the image and query privacy in multi-user scenarios. To solve the above problems, we first propose a basic privacy-preserving content-based image retrieval (CBIR) framework which significantly reduces storage and communication overhead compared with the previous works. Furthermore, we design a new efficient key conversion protocol to support unshared key multi-owner multi-user image retrieval without losing search precision. Moreover, our framework supports unbounded attributes and can trace malicious users according to leaked secret keys, which significantly improve the usability of multi-source data sharing. Strict security analysis shows that the user privacy and outsourced data security can be guaranteed during the image retrieval process, and the performance analysis using real-world dataset shows that the proposed image retrieval framework is efficient and feasible for practical applications.

The Internet of Things (IoT)-based health system provides patients and doctors a lot of conveniences, doctors can diagnose patients in time through monitored health data. However, doctors may make a wrong diagnosis of the patient's illness, if the health data stored on the cloud is tampered or lost due to an external attack or power failure. Therefore, it is of great importance to verify the integrity of the patient's health data stored on the cloud. Existing data integrity verification technologies usually need data owner to compute data authenticators for verification, but sensors on a patient in IoT-based health system have limited computation ability, thus existing data integrity verification technologies are not very suitable in IoT-based health system. This paper proposes a lightweight secure IoT-based health storage system to solve this problem. The proposed system employs edge server to compute data authenticators and verify data integrity, greatly reduces the system's computation cost and management burden of third party verifier. Security analysis and performance evaluation show the proposed system is feasible.

Online medical primary diagnosis system, which can provide convenient medical decision support through applying mobile communication and data analysis technology, has been considered as a promising approach to improve the quality of healthcare service. However, it still faces many severe challenges on the privacy of users' health information and the accuracy of diagnosis result, which deter the wide adoption of online medical primary diagnosis system. In this paper, we propose an efficient and privacy-preserving online medical primary diagnosis (CINEMA) framework. Within CINEMA framework, users can access online medical primary diagnosing service accurately without divulging their medical data. Specifically, based on fast secure permutation and comparison technique, the encrypted user's query is directly operated at the service provider (SP) without decryption, and the diagnosis result can only be decrypted by the user, meanwhile, the diagnosis model in SP can also be protected. Through extensive analysis, we show that CINEMA can ensure that user's health information and healthcare SP's diagnosis model are kept confidential, and has significantly reduce computation and communication overhead. In addition, performance evaluations via implementing CINEMA demonstrate its effectiveness in term of the real environment.

Nowadays, outsourcing data and machine learning tasks, e.g.,$k$-nearest neighbor (KNN) classification, to clouds has become a scalable and cost-effective way for large scale data storage, management, and processing. However, data security and privacy issue have been a serious concern in outsourcing data to clouds. In this article, we propose a privacy-preserving KNN classification scheme on cloud data in a twin-cloud model based on an additively homomorphic cryptosystem and secret sharing. Compared with existing works, we redesign a set of lightweight building blocks, such as secure square Euclidean distance, secure comparison, secure sorting, secure minimum, and maximum number finding, and secure frequency calculating, which achieve the same security level but with higher efficiency. In our scheme, data owners stay offline, which is different from secure-multiparty computation-based solutions which require data owners’ stay online during computation. In addition, query users do not interact with the cloud except sending query data and receiving the query results. Our security analysis shows that the scheme protects outsourced data security and query privacy, and hides access patterns. The experiments on real-world dataset indicate that our scheme is significantly more efficient than existing schemes.

Most of the current intelligent Internet of Things (IoT) products take neural network-based speech recognition as the standard human–machine interaction interface. However, the traditional speech recognition frameworks for smart IoT devices always collect and transmit voice information in the form of plaintext, which may cause the disclosure of user privacy. Due to the wide utilization of speech features as biometric authentication, the privacy leakage can cause immeasurable losses to personal property and privacy. Therefore, in this paper, we propose an outsourced privacy-preserving speech recognition framework (OPSR) for smart IoT devices in the long short-term memory (LSTM) neural network and edge computing. In the framework, a series of additive secret sharing-based interactive protocols between two edge servers are designed to achieve lightweight outsourced computation. And based on the protocols, we implement the neural network training process of LSTM for intelligent IoT device voice control. Finally, combined with the universal composability theory and experiment results, we theoretically prove the correctness and security of our framework.

The development of machine learning technology and visual sensors is promoting the wider applications of face recognition into our daily life. However, if the face features in the servers are abused by the adversary, our privacy and wealth can be faced with great threat. Many security experts have pointed out that, by 3-D-printing technology, the adversary can utilize the leaked face feature data to masquerade others and break the E-bank accounts. Therefore, in this paper, we propose a lightweight privacy-preserving adaptive boosting (AdaBoost) classification framework for face recognition (POR) based on the additive secret sharing and edge computing. First, we improve the current additive secret sharing-based exponentiation and logarithm functions by expanding the effective input range. Then, by utilizing the protocols, two edge servers are deployed to cooperatively complete the ensemble classification of AdaBoost for face recognition. The application of edge computing ensures the efficiency and robustness of POR. Furthermore, we prove the correctness and security of our protocols by theoretic analysis. And experiment results show that, POR can reduce about 58% computation error compared with the existing differential privacy-based framework.

Cloud-assisted Internet of Things (IoT) is increasingly prevalent in our society, for example in home and office environment; hence, it is also known as cloud-assisted Internet of Everything (IoE). While in such a setup, data can be easily shared and disseminated (e.g., between a device, such as Amazon Echo and the cloud, such as Amazon AWS), there are potential security considerations that need to be addressed. Thus, a number of security solutions have been proposed. For example, searchable encryption (SE) has been extensively studied due to its capability to facilitate searching of encrypted data. However, threat models in most existing SE solutions rarely consider the malicious data owner and semi-trusted cloud server at the same time, particularly in dynamic applications. In a real-world deployment, disputes between above two parties may arise as either party will accuse the other of some misbehavior. Furthermore, efficient full-update operations (e.g., data modification, data insertion, and data deletion) are not typically supported in the cloud-assisted IoE deployment. Therefore, in this paper, we present a fair and dynamic data sharing framework (FairDynDSF) in the multiowner setting. Using FairDynDSF, one can check the correctness of search results, achieve fair arbitration, multikeyword search, and dynamic update. We also prove that FairDynDSF is secure against inside keyword guessing attack and demonstrate its efficiency by evaluating its performance using various datasets.

Ciphertext-policy attribute-based keyword search (CP-ABKS) schemes facilitate the fine-grained keyword search over encrypted data, such as those sensed/collected from Industrial Internet of Things (IIoT) devices and stored in the cloud. However, existing CP-ABKS schemes generally have significant computation and storage requirements, which are beyond those of resource-constrained IIoT devices. Therefore, in this paper, we design a secure online/offline data sharing framework (DSF), which supports online/offline encryption and outsourced decryption. Using the healthcare setting as a case study, we demonstrate how DSF can be deployed in the cloud-assisted Healthcare IIoT (HealthIIoT) system. We not only prove that the DSF is selectively secure in the chosen access structure security model but also demonstrate its efficiency and feasibility in practical scenarios using experiments.

The past decade has witnessed the rise of crowdsourcing, and privacy in crowdsourcing has also gained rising concern in the meantime. Task matching or task subscription is one of indispensable services in crowdsourcing, but few mechanisms can achieve the expressive task subscription while protecting the privacy. In this paper, we focus on the privacy leaks and attacks during task subscription in crowdsourcing, and propose a privacy-preserving task subscription scheme with sybil detection, called SybSub. The SybSub scheme achieves the expressiveness of task subscription in the multisubscriber and multipublisher crowdsourcing while protecting the privacy of both subscribers and publishers against the semi-honest crowdsourcing service provider, and meanwhile supports the sybil attack detection against greedy subscribers. We implement the SybSub scheme and evaluate it thoroughly. Performance results validate that the SybSub scheme is efficient and feasible.

As an important application of the Internet of Things technologies, mobile healthcare crowd sensing (MHCS) still has challenging issues, such as privacy protection and efficiency. Quite recently in the IEEE Internet of Things Journal (DOI: 10.1109/JIOT.2018.2828463), Liuet al.proposed a large-scale concurrent data anonymous batch verification scheme for MHCS, claiming to provide batch authentication, nonrepudiation, and anonymity. However, after a close look at the scheme, we point out that the scheme suffers two types of signature forgery attacks and hence fails to achieve the claimed security properties. In addition, a reasonable and rigorous probability analysis indicates that the security reduction from the security of the scheme to the hardness of the computational Diffie–Hellman problem is invalid. We hope that similar design flaws can be avoided in future design of anonymous batch verification schemes for MHCS.

Equipped with the emerging cloud computing, clients prefer to outsource the increasing number of Industrial Internet of things (IIoT) data to cloud to reduce the high storage and computation burden. However, existing searchable encryption (SE) schemes just apply to IIoT records containing textual keyword fields rather than both digital and textual keyword ones. Besides, the key management issue still impedes the practicality and availability of SE schemes due to high key storage overhead. To this end, we present an outsourced Hybrid Keyword-Field Search over encrypted data with efficient Keys Management (HKFS-KM) scheme by utilizing the relevance score function and keyed hash tree. Formal security analysis proves that the HKFS-KM scheme can achieve keyword privacy and trapdoor unlinkability in both known ciphertexts attack model and known background attack model. Experimental results using real-world dataset show its efficiency and practicality in practice.

Fog computing, as an extension of cloud computing, outsources the encrypted sensitive data to multiple fog nodes on the edge of Internet of Things (IoT) to decrease latency and network congestion. However, the existing ciphertext retrieval schemes rarely focus on the fog computing environment and most of them still impose high computational and storage overhead on resource-limited end users. In this paper, we first present a Lightweight Fine-Grained ciphertexts Search (LFGS) system in fog computing by extending Ciphertext-Policy Attribute-Based Encryption (CP-ABE) and Searchable Encryption (SE) technologies, which can achieve fine-grained access control and keyword search simultaneously. The LFGS can shift partial computational and storage overhead from end users to chosen fog nodes. Furthermore, the basic LFGS system is improved to support conjunctive keyword search and attribute update to avoid returning irrelevant search results and illegal accesses. The formal security analysis shows that the LFGS system can resist Chosen-Keyword Attack (CKA) and Chosen-Plaintext Attack (CPA), and the simulation using a real-world dataset demonstrates that the LFGS system is efficient and feasible in practice.

The past decade has witnessed the rise of crowdsourcing, and privacy in crowdsourcing has also gained rising concern in the meantime. In this paper, we focus on the privacy leaks and sybil attacks during the task matching, and propose a privacy-preserving task matching scheme, called SybMatch. The SybMatch scheme can simultaneously protect the privacy of publishers and subscribers against semi-honest crowdsourcing service provider, and meanwhile support the sybil detection against greedy subscribers and efficient user revocation. Detailed security analysis and thorough performance evaluation show that the SybMatch scheme is secure and efficient.

With the development of virtualization technology and fast expansion of network-scale, SDN has been employed in various cases from campus networks to cloud data center networks. However, SDN networks are also facing some new security issues, relative to the traditional networks. In this work, we demonstrate a novel network isolation attack in SDN networks, called Network Harvesting, that lets an attacker can access to the user's network privileges without the awareness of victim and OpenFlow SDN architecture, which significantly increases persistence. We then present a defense, SpoofDefender, that prevents network isolation attacks or other spoofing attacks by leveraging SDN's data and control plane separation, global network view, and programmatic control of the network, while building upon IEEE 802.1x and encryption. In addition, we also implement SpoofDefender on ONOS 1.10.4 and Mininet with a real network, and extensive simulation results demonstrate that our proposed SpoofDefender is highly effective in terms of computation and communication costs.

Online medical primary diagnosis system, which can provide the pre-diagnosis service anywhere anytime, has attracted considerable interest. However, the flourish of online medical primary diagnosis system still faces many serious challenges since the sensitivity of personal health information and service provider''s diagnosis model. In this paper, we propose an efficient and privacy-preserving medical primary diagnosis scheme based on k-nearest-neighbors classification (kNN), called EPDK. With EPDK, medical users can ensure that their sensitive health information are not compromised during the online medical diagnosis process, and service provider can provide high-accuracy service without revealing its diagnosis model. Specifically, based on lightweight multiparty random masking and polynomial aggregation techniques, a medical user preprocesses her/his query vector before sending out and the preprocessed vector is directly operated in the service provider without obtaining original data, meanwhile, the primary diagnosis result cannot be achieved by anyone except the medical user. Through extensive analysis, we show that EPDK can resist multifarious known security threats, and has significantly lower computation complexity than existing schemes. Moreover, performance evaluations via implementing EPDK in the real environment demonstrate that EPDK is highly efficient in terms of computation overhead.

Cloud-based mobile crowd-sourcing has been an attractive solution to provide data storage and share services for resource-limited mobile devices in a privacy-preserving manner, but how to enable mobile users to issue search queries and achieve fine-grained access control over ciphertexts simultaneously is still a big challenge for various circumstances. Although the ciphertext-policy attribute-based keyword search technology combining attribute-based encryption with searchable encryption has become a hot research topic, it just deals with equivalent attributes rather than more practical attribute comparisons, like “greater than” or “less than.” In this paper, we devise a practical cryptographic primitive called attribute-based multi-keyword search scheme to support comparable attributes through utilizing 0-encoding and 1-encoding. Formal security analysis proves that our scheme is selectively secure against chosen-keyword attack in generic bilinear group model and extensive experiments using real-world dataset demonstrate that our scheme can drastically decrease both computational and storage costs.

With the development of sharing economy, crowdsourcing as a distributed computing paradigm has become increasingly pervasive. As one of indispensable services for most crowdsourcing applications, task matching has also been extensively explored. However, privacy issues are usually ignored during the task matching and few existing privacy-preserving crowdsourcing mechanisms can simultaneously protect both task privacy and worker privacy. This paper systematically analyzes the privacy leaks and potential threats in the task matching and proposes a single-keyword task matching scheme for the multirequester/multiworker crowdsourcing with efficient worker revocation. The proposed scheme not only protects data confidentiality and identity anonymity against the crowd-server, but also achieves query traceability against dishonest or revoked workers. Detailed privacy analysis and thorough performance evaluation show that the proposed scheme is secure and feasible.

Functional encryption (FE) is a vast new paradigm for encryption scheme which allows tremendous flexibility in accessing encrypted data. In a FE scheme, a user can learn specific function of encrypted messages by restricted functional key and reveals nothing else about the messages. Besides the standard notion of data privacy in FE, it should protect the privacy of the function itself which is also crucial for practical applications. In this paper, we construct a secret key FE scheme for the inner product functionality using asymmetric bilinear pairing groups of prime order. Compared with the existing similar schemes, our construction reduces both necessary storage and computational complexity by a factor of 2 or more. It achieves simulation-based security, security strength which is higher than that of indistinguishability-based security, against adversaries who get hold of an unbounded number of ciphertext queries and adaptive secret key queries under the External Decisional Linear (XDLIN) assumption in the standard model. In addition, we implement the secret key inner product scheme and compare the performance with the similar schemes.

In this paper, we propose a framework for efficient and privacy-preserving outsourced calculation of rational numbers, which we refer to as POCR. Using POCR, a user can securely outsource the storing and processing of rational numbers to a cloud server without compromising the security of the (original) data and the computed results. We present the system architecture of POCR and the associated toolkits required in the privacy preserving calculation of integers and rational numbers to ensure that commonly used outsourced operations can be handled on-the-fly. We then prove that the proposed POCR achieves the goal of secure integer and rational number calculation without resulting in privacy leakage to unauthorized parties, and demonstrate the utility and the efficiency of POCR using simulations.

Healthcare Internet-of-things (IoT) has been proposed as a promising means to greatly improve the efficiency and quality of patient care. Medical devices in healthcare IoT measure patients' vital signs and aggregate these data into medical files which are uploaded to the cloud for storage and accessed by healthcare workers. To protect patients' privacy, encryption is normally used to enforce access control of medical files by authorized parties while preventing unauthorized access. In healthcare, it is crucial to enable timely access of patient files in emergency situations. In this paper, we propose a lightweight break-glass access control (LiBAC) system that supports two ways for accessing encrypted medical files: attribute-based access and break-glass access. In normal situations, a medical worker with an attribute set satisfying the access policy of a medical file can decrypt and access the data. In emergent situations, the break-glass access mechanism bypasses the access policy of the medical file to allow timely access to the data by emergency medical care or rescue workers. LiBAC is lightweight since very few calculations are executed by devices in the healthcare IoT network, and the storage and transmission overheads are low. LiBAC is formally proved secure in the standard model and extensive experiments are conducted to demonstrate its efficiency.

Affording secure and efficient big data aggregation methods is very attractive in the field of wireless sensor networks (WSNs) research. In real settings, the WSNs have been broadly applied, such as target tracking and environment remote monitoring. However, data can be easily compromised by a vast of attacks, such as data interception and data tampering, etc. In this paper, we mainly focus on data integrity protection, give an identity-based aggregate signature (IBAS) scheme with a designated verifier for WSNs. According to the advantage of aggregate signatures, our scheme not only can keep data integrity, but also can reduce bandwidth and storage cost for WSNs. Furthermore, the security of our IBAS scheme is rigorously presented based on the computational Diffie-Hellman assumption in random oracle model.

In this paper, we propose a new efficient privacy-preserving outsourced computation framework over public data, called EPOC. EPOC allows a user to outsource the computation of a function over multi-dimensional public data to the cloud while protecting the privacy of the function and its output. Specifically, we introduce three types of EPOC in order to tradeoff different levels of privacy protection and performance. We present a new cryptosystem called Switchable Homomorphic Encryption with Partially Decryption (SHED) as the core cryptographic primitive for EPOC. We introduce two coding techniques, called message pre-coding technique and message extending and coding technique respectively, for messages encrypted under a composite order group. Furthermore, we propose a Secure Exponent Calculation Protocol with Public Base (SEPB), which serves as the core sub-protocol in EPOC. Detailed security analysis shows that the proposed EPOC achieves the goal of outsourcing computation of a private function over public data without privacy leakage to unauthorized parties. In addition, performance evaluations via extensive simulations demonstrate that EPOC is efficient in both computation and communications.

In this paper, we propose a framework for privacy-preserving outsourced functional computation across large-scale multiple encrypted domains, which we refer to as POFD. With POFD, a user can obtain the output of a function computed over encrypted data from multiple domains while protecting the privacy of the function itself, its input and its output. Specifically, we introduce two notions of POFD, the basic POFD and its enhanced version, in order to tradeoff the levels of privacy protection and performance. We present three protocols, named Multi-domain Secure Multiplication protocol (MSM), Secure Exponent Calculation protocol with private Base (SECB), and Secure Exponent Calculation protocol (SEC), as the core sub-protocols for POFD to securely compute the outsourced function. Detailed security analysis shows that the proposed POFD achieves the goal of calculating a user-defined function across different encrypted domains without privacy leakage to unauthorized parties. Our performance evaluations using simulations demonstrate the utility and the efficiency of POFD.

In this paper, we propose a toolkit for efficient and privacy-preserving outsourced calculation under multiple encrypted keys (EPOM). Using EPOM, a large scale of users can securely outsource their data to a cloud server for storage. Moreover, encrypted data belonging to multiple users can be processed without compromising on the security of the individual user's (original) data and the final computed results. To reduce the associated key management cost and private key exposure risk in EPOM, we present a distributed two-trapdoor public-key cryptosystem, the core cryptographic primitive. We also present the toolkit to ensure that the commonly used integer operations can be securely handled across different encrypted domains. We then prove that the proposed EPOM achieves the goal of secure integer number processing without resulting in privacy leakage of data to unauthorized parties. Last, we demonstrate the utility and the efficiency of EPOM using simulations.

In this paper, we propose a framework for privacy-preserving outsourced calculation on floating point numbers (POCF). Using POCF, a user can securely outsource the storing and processing of floating point numbers to a cloud server without compromising on the security of the (original) data and the computed results. In particular, we first present privacy-preserving integer processing protocols for common integer operations. We then present an approach to outsourcing floating point numbers for storage in a privacy-preserving way, and securely processing commonly used floating point number operations on-the-fly. We prove that the proposed POCF achieves the goal of floating point number processing without privacy leakage to unauthorized parties, and demonstrate the utility and the efficiency of POCF using simulations.

Clinical decision support system, which uses advanced data mining techniques to help clinician make proper decisions, has received considerable attention recently. The advantages of clinical decision support system include not only improving diagnosis accuracy but also reducing diagnosis time. Specifically, with large amounts of clinical data generated everyday, naïve Bayesian classification can be utilized to excavate valuable information to improve a clinical decision support system. Although the clinical decision support system is quite promising, the flourish of the system still faces many challenges including information security and privacy concerns. In this paper, we propose a new privacy-preserving patient-centric clinical decision support system, which helps clinician complementary to diagnose the risk of patients' disease in a privacy-preserving way. In the proposed system, the past patients' historical data are stored in cloud and can be used to train the naïve Bayesian classifier without leaking any individual patient medical data, and then the trained classifier can be applied to compute the disease risk for new coming patients and also allow these patients to retrieve the top- k disease names according to their own preferences. Specifically, to protect the privacy of past patients' historical data, a new cryptographic tool called additive homomorphic proxy aggregation scheme is designed. Moreover, to leverage the leakage of naïve Bayesian classifier, we introduce a privacy-preserving top- k disease names retrieval protocol in our system. Detailed privacy analysis ensures that patient's information is private and will not be leaked out during the disease diagnosis phase. In addition, performance evaluation via extensive simulations also demonstrates that our system can efficiently calculate patient's disease risk with high accuracy in a privacy-preserving way.

Abstract In multi‐authority attribute‐based encryption (ABE) systems, each authority manages a different attribute universe and issues the private keys to users. However, the previous multi‐authority ABE schemes are subject to such restrictions during initializing the systems: either the attribute universe is polynomially sized and the attributes have to be enumerated or the attribute universe can be exponentially large, but the size of the set of attributes, which will be used in encryption, is not more than a predefined fixed value. These restrictions prevent multi‐authority ABE schemes from being deployed in dynamic practice applications. In this paper, we present a large universe decentralized key‐policy ABE scheme without such additional limitation. In our scheme, there is no requirement of any central authority. Each attribute authority executes independently from the others and can join or depart the system allodiality. Our system supports any monotone access policy. The proposed scheme is constructed on prime order groups and proved selectively secure in the standard model. To the best of our knowledge, our scheme is the first large universe decentralized key‐policy ABE system in the standard model. Copyright © 2014 John Wiley & Sons, Ltd.

Abstract Multi‐authority attribute‐based encryption (ABE) is a generation of ABE where the descriptive attributes are managed by different authorities. In current multi‐authority ABE schemes, the scale of attribute universe employed in encryption is restricted by various predefined thresholds. In this paper, we propose an unbounded multi‐authority ciphertext‐policy ABE system without such restriction. Our scheme consists of multiple attribute authorities (AAs), one central authority (CA), and users labeled by the set of attributes. Each AA governs a different universe of attributes and operates separately. Moreover, there is no cooperation between the CA and AAs. To provide the private keys for a user, the AAs first issue partial attribute‐related keys according to the attributes; the CA then issues identity‐related keys and links these attribute‐keys with the user's global identifier. Both the identity‐related and the linked attribute‐related keys will be used in decryption. The proposed multi‐authority ciphertext‐policy ABE scheme can support arbitrary linear secret sharing scheme as the access policy. Performance analysis and security proof indicate that our scheme is efficient and secure. Copyright © 2015 John Wiley & Sons, Ltd.

In service-oriented mobile social networks (S-MSN), many location-based services are developed to provide various applications to social participants. Services can in turn be composed with the help of these participants. However, the composite structure, the subjective interpretation of trust demand, and the opportunistic connectivity make service composition a challenging task in S-MSN. In this paper, we propose a novel approach to enable trustworthy service evaluation and invocation during the process of composition. By analyzing dependency relationships, our approach can decentralizedly evaluate the trust degree of each service based on a lattice-based trust model to prevent data from being transmitted to untrustworthy counterparts. Besides, service consumers and vendors are able to specify their global and local constraints on the trust degree of service components on demand for more effective composition. Finally, by introducing acquaintances to the neighbors iteratively, social participants form a trust-aware acquaintance graph to forward invocation messages.

Attribute‐based encryption (ABE) has been considered as a promising cryptographic primitive for realising information security and flexible access control. However, the characteristic of attributes is treated as the identical level in most proposed schemes. Lattice‐based cryptography has been attracted much attention because of that it can resist to quantum cryptanalysis. In this study, lattice‐based threshold hierarchical ABE (lattice‐based t ‐HABE) scheme without random oracles is constructed and proved to be secure against selective attribute set and chosen plaintext attacks under the standard hardness assumption of the learning with errors problem. The notion of the HABE scheme can be considered as the generalisation of traditional ABE scheme where all attributes have the same level.

With the rapid development of versatile cloud services, it becomes increasingly susceptible to use cloud services to share data in a friend circle in the cloud computing environment. Since it is not feasible to implement full lifecycle privacy security, access control becomes a challenging task, especially when we share sensitive data on cloud servers. In order to tackle this problem, we propose a key-policy attribute-based encryption with time-specified attributes (KP-TSABE), a novel secure data self-destructing scheme in cloud computing. In the KP-TSABE scheme, every ciphertext is labeled with a time interval while private key is associated with a time instant. The ciphertext can only be decrypted if both the time instant is in the allowed time interval and the attributes associated with the ciphertext satisfy the key's access structure. The KP-TSABE is able to solve some important security problems by supporting user-defined authorization period and by providing fine-grained access control during the period. The sensitive data will be securely self-destructed after a user-specified expiration time. The KP-TSABE scheme is proved to be secure under the decision l-bilinear Diffie-Hellman inversion (l-Expanded BDHI) assumption. Comprehensive comparisons of the security properties indicate that the KP-TSABE scheme proposed by us satisfies the security requirements and is superior to other existing schemes.