We report a structural mismatch between a data point’s {learnability}—how quickly it improves the loss—and its {forgettability}—how much it anchors the final parameters—an aspect ignored by prior machine unlearning frameworks such as SISA, Fisher-Forget, and influence-based fine-tuning. To make this gap measurable we introduce Unlearning Gradient Sensitivity (UGS), an influence score computable with a single Hutch++ sketch, and derive the Learnability–Forgettability Divergence (LFD), the Jensen–Shannon distance between the model’s learning and forgetting distributions. We prove that UGS dispersion decays exponentially only under explicit regularisation and that LFD converges to zero when its weight grows sub-linearly relative to the UGS term. Building on these findings, we introduce Dual-Aware Training (DAT)—a lightweight regularization method that reduces variability in how easily data points can be forgotten and aligns learning and forgetting behaviors during training. On CIFAR-10, MNIST, and IMDB, DAT maintains the original model accuracy while cutting forgettability divergence in half and significantly lowering the cost of certified unlearning, showing that it’s effective to make models forgettable from the start.

Graph-based multi-task learning at billion-scale presents a significant challenge, as different tasks correspond to distinct billion-scale graphs. Traditional multi-task learning methods often neglect these graph structures, relying solely on individual user and item embeddings. However, disregarding graph structures overlooks substantial potential for improving performance. In this paper, we introduce the Macro Graph of Experts (MGOE) framework, the first approach capable of leveraging macro graph embeddings to capture task-specific macro features while modeling the correlations between task-specific experts. Specifically, we propose the concept of a Macro Graph Bottom, which, for the first time, enables multi-task learning models to incorporate graph information effectively. We design the Macro Prediction Tower to dynamically integrate macro knowledge across tasks. MGOE has been deployed at scale, powering multi-task learning for a leading billion-scale recommender system, Alibaba. Extensive offline experiments conducted on three public benchmark datasets demonstrate its superiority over state-of-the-art multi-task learning methods, establishing MGOE as a breakthrough in multi-task graph-based recommendation. Furthermore, online A/B tests confirm the superiority of MGOE in billion-scale recommender systems.

Vision Transformers (ViTs) have emerged as a dominant backbone architecture for a variety of visual tasks; however, their vulnerability to adversarial examples continues to pose a significant challenge. Unlike Convolutional Neural Networks (CNNs), ViTs fundamentally rely on self-attention mechanisms, leading to a distinct architectural design. The limited transferability of existing adversarial attacks on ViTs can be attributed to the neglect of these unique features. To address this, we introduce a novel self-attention-oriented Adversarial Block Skip (ABS) method specifically designed to generate transferable adversarial examples. ABS aims to create a diverse range of structures by applying skip connections to blocks within the transformer encoder, thereby activating the uncertainty of the attention mechanism. This disrupts the global interaction between different features captured by ViTs, thereby confounding the model's decision-making process. The results unequivocally demonstrate that the ABS not only establishes a versatile and efficacious attack mechanism but also supports transfer attacks across a diverse array of ViTs and CNNs. This finding emphasizes the significant generalization capabilities of ViTs within the adversarial landscape, suggesting that their resilience and adaptability under such conditions may surpass previous assumptions. Comprehensive empirical evaluations involving various prominent transformer models on the ImageNet dataset substantiate that ABS markedly surpasses existing baseline methods in terms of effectiveness. Furthermore, ABS is highly compatible with prevailing adversarial attack frameworks, augmenting their efficacy upon integration. Such versatility renders ABS an indispensable component of the toolkit for executing advanced and effective adversarial attacks in the realm of machine learning security.

Dynamic searchable symmetric encryption (DSSE) allows a client to update and retrieve its encrypted database stored on a server. To enable the database contributed by multi-writers to be searched by multi-readers, the multi-writer/multi-reader model is explored for DSSE (M/M-DSSE). Recently, FP-HSE (USENIX Security'22) and FP-MSE (TDSC'24) employed key aggregation methodology to introduce writer-selection property for M/M-DSSE, where a reader uses a single aggregate key to search the database containing selective writers. However, they neglected the reader-selection property where a writer selects which readers can search its data, and only supported single-keyword search. In this paper, we present BiMM, a conjunctive M/M-DSSE scheme with bilateral selection that simultaneously supports writer-selection and reader-selection properties. Additionally, BiMM achieves forward privacy (FP) for both server and client, and Type-O backward privacy (BP). Technically, we introduce a new primitive called bilateral key-aggregate encryption (Bi-KAE) that refines KAE via distributed key generation, by which both writers and readers can specify their selections. Based on ODXT (NDSS'21) that provides conjunctive queries while achieving FP with server and BP, we introduce double-blinded values to match all update records for the search keywords and additionally use the 0/1-Encoding technique to consider FP with client. Besides presenting formal security analysis for BiMM, we also conduct extensive experiments over public datasets on a real cloud server environment. The experiment results demonstrate that BiMM achieves practical performance for desired properties. With #keyword = 50 and #s-term = 10 for conjunctive queries, BiMM runs 6.34× faster than Nomos (AsiaCCS'24) which does not consider either writer-selection or reader-selection.

Federated Transfer Learning (FTL) is a popular approach to solve the problem of heterogeneous feature space and label distribution. Among the mainstream strategies for FTL, parameter decoupling, which balance the impact of a single global model and multiple personalized models under data heterogeneity, has attracted the attention of many researchers. However, few attacks have been proposed to evaluate the privacy risk of FTL. We find that the fine-tuned structures and the gradient update mechanisms of parameter decoupling would be more likely to leak personalized information for the server to infer private labels. Based on our findings, we propose the label inference attack that combines meta classifier with contrastive learning in FTL. Our experiments show that the proposed attack has ability to extract local personalized information from the differences before and after fine-tuning to improve the accuracy of the attack in the absence of a downstream model. Our research can reveal potential privacy risks in FTL and motivate more research on private and secure FTL.

Applying differential privacy (DP) to federated learning (FL) effectively safeguards participants’ training data against privacy threats, yet the stringent availability requirements of FL present a significant challenge in optimizing accuracy while ensuring privacy. Integrating differential privacy continuous data release (DPCR) into private FL mitigates the errors accumulating on intermediate parameter models securely, thereby enhancing accuracy, with performance gains driven by developing advanced DPCR models. In this context, we propose ak-ary Tree-based DPCR (kTCR) model to provide deeper and more flexible error optimization, thereby promoting a robust accuracy enhancement for private FL. Our kTCR model introduces Variance Optimal Estimation (VOE) and privacy budget allocation (PBA) methods to optimize accuracy, posing significant efficiency challenges simultaneously. With rigorous mathematical analysis, we reduce the computational complexity of VOE fromO(t3) toO(lgt), then introduce a meta-factor method that transforms the challenging PBA issues into a convex optimization problem with significantly reduced variables (e.g., a 3-ary tree with 5.23 × 109nodes requiring only 61 variables), thus yielding high efficiencies. Our experiments on classical datasets demonstrate that our kTCR model with appropriatekoutperforms the state-of-the-art ABCRG by 0.7% ~ 2.0% in accuracy and traditional private FL by 5.5% ~ 18.7%. Further experiments demonstrate that adjusting the aritykeffectively reduces the Pre-aggregation Error, leading to a further 2.09% accuracy gain. Our achievements both improve the accuracy of private FL and provide new insights into building high-availability FL with DP.

Privacy preservation are becoming increasingly significant in machine learning, with recent privacy regulations requiring the deletion of personal data and its impact on models. Although erasing data from storage is simple, removing the influence of data on models remains a challenge. Federated unlearning is an emerging paradigm that aims to forget the knowledge contributed by some specific data to the federated model. In this paper, we design a novel federated unlearning strategy, named FedWiper, which enables exact unlearning in federated learning by erasing specific data and its impact from the federated model. Specifically, based on the granularity of the dataset, we propose training multiple federated submodels to construct a federated unlearning framework, thereby narrowing the scope of the impact of wiped data. Furthermore, the proposed Uni-Adapter structure effectively mitigates the negative impact on model performance from diminishing the dataset scale, while also reducing communication cost. Rather than focusing solely on achieving indistinguishability unlearning of the model for classification task, we extend FedWiper to unlearning for multiple types of tasks and achieve the exact unlearning. Experiments demonstrate that FedWiper can not only accelerate federated unlearning, but also achieve exact unlearning across multiple types of tasks in federated learning while ensuring minimal loss of model performance. Our Code: https://github.com/grey1989/FedWiper.

Semantic segmentation is a pivotal research area in the advancement of autonomous driving, with a particular focus on addressing adverse weather conditions such as night, rain, and fog. However, a challenging problem that remains is effectively segmenting environments that contain multiple adverse factors within the same scene. To tackle this issue, we present SCDF, an adaptive semantic segmentation approach. SCDF employs two separate image processing modules for denoising and enhancement of low-quality inputs. To enhance the denoising effect, we also optimized the loss function of its defogging module. Furthermore, we proposed a novel weight adaptation module, which enables SCDF to switch between different driving scenarios. To evaluate the effectiveness of SCDF, we conduct experiments on the ACDC and Rainy & Foggy cityscapes datasets, respectively achieving a higher mean Intersection over Union (mIoU) score of 61.4%(ACDC) and 79.1%(Rainy & Foggy Cityscapes). This promising results demonstrate the potential of SCDF in significantly improving the performance of autonomous driving systems in complex environments with multiple adverse factors.

In the era of the Internet of Things (IoT), managing the deluge of data generated by distributed devices presents unique challenges, particularly concerning privacy and the efficient use of computational resources. Vertical Federated Learning (VFL) offers a promising avenue for collaborative machine learning without centralizing data, thereby addressing privacy concerns inherent in traditional approaches. However, as data privacy laws and personal data deletion requests become more prevalent, the necessity for effective machine unlearning strategies within VFL frameworks grows increasingly important. To this end, this paper introduces a novel approach to feature-based machine unlearning tailored specifically for VFL systems in IoT networks. Our methodology enables the selective removal of data influence from trained models without the need for full retraining, thus preserving model utility while ensuring compliance with privacy requirements. By integrating a combination of feature relevance measuring techniques and efficient communication protocols, our solution minimizes the data footprint on network nodes, reduces bandwidth consumption, and maintains the integrity and performance of the learning models. To the best of our knowledge, our proposed framework represents the first practical approach to enable machine unlearning within vertical federated learning environments. We demonstrate the effectiveness of our approach through rigorous evaluation using several IoT datasets, highlighting significant improvements in unlearning efficiency and model robustness compared to existing techniques. Our work not only furthers the development of sustainable and compliant machine learning models in IoT but also sets a foundational framework for future research in secure and efficient data management within federated environments.

In the field of industrial production, anomaly detection is crucial for ensuring product quality and maintaining production efficiency. With the continuous advancement of computer vision technology, it has shown tremendous potential in industrial applications. However, the scarcity of labeled anomaly samples in real-world operating environments poses significant challenges for traditional anomaly detection techniques. To address this, we propose MemADet, a novel anomaly detection model that employs an unsupervised approach and leverages a representative memory bank. It employs a dynamic decision mechanism to control the representativeness of the features stored in the memory bank, and employs a weighted anomaly score calculation mechanism to further enhance the performance of image anomaly detection. Our evaluations indicate that MemADet performs robustly in industrial image anomaly detection across three datasets, with particularly no-table detection accuracy on the MVTec AD dataset. Its efficacy is further validated by competitive results on two additional datasets, highlighting its consistent and effective performance in various settings.

Applications in Engineering: In industry, surface defect detection is crucial for improving product quality . However, there are many challenges in industrial inspection scenarios, such as interference from background noise, complex small-target problems, significant variations in target objects, and the problem of finding a balance between inspection speed and accuracy. To address the above problems, this paper proposes an industrial defect-aware network based on cross-layer semantic information guidance and contextual attention enhancement (IDP-Net). Specifically, IDP-Net has four different new features. The contribution of artificial intelligence : Firstly, to solve the industrial surface context and defect similarity problem, this paper proposes a Lightweight Local Global Feature Extraction Network (LLG-Net), unlike other methods, the effective combination of self-attention blocks and convolution blocks ensures gradual integration of global and local features across multiple layers, to improve the detection ability of targets with significant changes in scale, this paper designs a Multiscale Perceptual Feature Aggregation Network (MPA-Net), adequately fuses the shallow fine-grained information and the deep semantic information. Then, to enhance the connection between multi-scale semantic information, an adaptive cross-layer feature fusion module (ACFF) is proposed, which is novel in integrating the characteristics of multiple adjacent levels to help the model better capture the different scale characterisation of the target. Finally, a Region Attention Module (RAM) is proposed and introduced in the detector to enhance the attention to the critical regions around the target object. In particular, this paper proposes a new localisation loss function (MEIoU) that enhances the network’s attention to objects at different scales. The experimental results show that 94.3%, 98.7% and 99.5% of [email protected] are obtained on steel, PCB and aluminium surface defect datasets, respectively, and 50 FPS is achieved, which is better than the current mainstream detectors and meets the demand of practical industrial production.

Multi-label text classification is a method for categorizing textual data based on features extracted from the original textual information. When it comes to modelling text structural properties, Graph Convolutional Network (GCN) has demonstrated outstanding performance. However, most existing graph-based models do not model the structure of a single text unit and do not consider the sequence information in each document (e.g., word order). To resolve these issues and fully utilize the text’s structural and sequential details, a text classification model called Sequential GCN with Multi-Head Attention (SGCN-MHA) is proposed in this paper. For each text, a separate text graph is constructed in which nodes are the words of the text, and the edges between nodes corresponding to the word relations. Then the GCN is used to extract the structural feature. To enable the word nodes in the document graph to hold contextual information, the BiLSTM is also applied to learn the sequential feature for each graph. Finally, the Multi-Head Attention mechanism is adopted to interact with these two features and then aggregate them to get access to critical information in the text. The efficiency of our approach has been tested on two standard datasets, including comparative and ablation experiments.

Abstract With the refinement and development of the Vehicle to Everything (V2X) concept, its security issues have gradually come to the fore, revealing many security risks and increasing security requirements for V2X, and many protective measures have likewise emerged. The article first introduces the development history of the past Internet of Vehicles(IoV), summarizes some common V2X security threats, surveys the security technologies used for V2X communication, and outlines the development of each technology and the proposed security protocols in the last 3 years. Due to the different advantages and disadvantages of previous protection schemes, the idea of using National Cryptography to supplement the security scheme or designing a new security scheme article based on the National Cryptography Algorithms((AKA SM algorithms) is proposed. The survey then introduces the SM2, SM3, SM9, and ZUC algorithms, describes the development and application of the SM commercial algorithm in recent years, and finally, statistics and introduces the part of the development process of the security protocols currently used in IoV regarding the SM algorithms and gives some application prospects.

Model stealing (MS) attacks pose a significant security concern for machine learning models on cloud platforms, as they can reconstruct a substitute model with limited effort to evade ownership. While detection-based methods show promise in preventing MS attacks, they often face practical challenges. Specifically, setting an appropriate threshold to distinguish malicious features from benign ones is a difficult task, often leading to a tradeoff between false alarm rates and detection accuracy. To address this challenge, we design a multidimensional feature extraction-and-distinction scheme called MED. It is achieved through a two-layer optimization: 1) the inner layer of extraction to maximize the difference of extracted multidimensional features between attack and benign samples and 2) the outer layer of distinction to maximize the accuracy of distinguishing malicious features automatically. Recognizing that different MS attacks result in varied features, we design a group of feature extraction functions in the inner layer optimization, which addresses the limitations of single-feature-based detection methods. Further, we employ three differently characterized models for distinction, enabling MED to distinguish different types of malicious features. Comprehensive experiments are conducted to evaluate the effectiveness of the proposed scheme: MED can detect all types of MS attacks with no more than 100 samples, with an average detection rate greater than 0.99.

Federated learning is a distributed machine learning approach that enables multiple participants to collaboratively train a model without sharing their data, thus preserving privacy. However, the decentralized nature of federated learning also makes it susceptible to backdoor attacks, where malicious participants can embed hidden vulnerabilities within the model. Addressing these threats efficiently and effectively is crucial, especially given the impracticality of iterative and resource-intensive detection methods in federated learning environments. This article presents a novel framework for one-shot backdoor removal in federated learning. Our approach integrates advanced anomaly detection techniques with a unique model update aggregation strategy, allowing for the identification and neutralization of backdoor influences in a single update cycle without the need for extensive data access or communication between participants. Extensive experiments across various federated architectures and data distributions demonstrate that our method effectively mitigates backdoor threats while maintaining model performance and scalability. This work not only enhances the security of federated models but also contributes to the broader applicability of federated learning in sensitive and critical domains.

Facing the global threat of endemic diseases, utilizing edge computing for exposure detection enables efficient monitoring of the dynamic distribution of infected patient groups across regions, enhancing the management and control of these diseases. Employing the quantitative exposure detection of endemic diseases, regions seek to reconcile patient information collected through mobile devices, aiming to obtain statistical and analytical results based on the intersection of patient lists. In this paper, we propose a privacy-preserving scheme for the collaborative quantitative exposure detection of endemic diseases, which ensures each region to only learn the statistical results, without any information about other regions' datasets. Our scheme is fundamentally achieved through Circuit-based Private Set Intersection (Circuit-PSI) that can compute functions over the set intersection without disclosing the intersection itself. However, the state-of-the-art solution involves a laborious process in which one party iteratively compares its elements with those of others, which leads to a significantly high communication complexity. Therefore, we introduce a novel multi-party protocol that can diminish the communication overhead of circuit-PSI through a skillful decoupling of the comparison complexity from the number of parties. To achieve this, we design a multiparty oblivious encoding scheme, which can prevent any party from inferring any private info through the encoded data. By filtering out the repeated elements, the comparison complexity is independent of the number of parties. Furthermore, to address scenarios involving patient information with additional attributes, we extend our protocol to include payloads by developing a lightweight multiparty data mapping algorithm. Our extensive experiments show that compared to prior works, our protocol achieves a substantial reduction in communication overhead by 6.4×, and runs 1.2× faster in the LAN setting and 3.1× in the WAN setting.

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.

Summary With the popularity of mobile Internet networks and mobile terminal equipment, mobile crowdsensing (MCS) has become a popular and economical way of data collection, sharing, and query services. However, the existing privacy‐preserving query schemes MCS‐based less consider the sensing user's privacy leakage at data aggregation phase and querier's privacy leakage at query service phase simultaneously. In this article, we propose a novel privacy‐preserving aggregation and query scheme applied in metro passenger flow via MCS, which achieves the metro passenger flow acquisition and query service and protects the sensing user's identity and location privacy as well as the querier's query privacy. We exploit Paillier cryptosystem and pseudonym mechanism to prevent the privacy leakage, and utilize secure kNN algorithm to protect the query privacy. Meanwhile, we achieve the sensing user accountability based on digital signature algorithm and credible management. The privacy analysis demonstrates that our scheme satisfies the privacy‐preserving and security requirements. The performance evaluation and experimental result show the efficiency of our scheme in practice.

Mobile crowdsensing (MCS) is widely applied in vehicular networks where several sensing vehicles complete the same sensing task. Recently, the privacy and reliability of sensing vehicles have aroused extensive attention of researchers in academia. Although the majority of existing schemes have achieved anonymous authentication with large computation and communication overheads, they do not take the reliability of sensing vehicles into account when selecting sensing vehicles. In this article, we propose an efficient anonymous authentication and privacy-preserving reliability evaluation (AARE) scheme for MCS, which not only improves the efficiency of mutual authentication but also guarantees the reliability of sensing vehicles. Specifically, an efficient anonymous authentication method is proposed to achieve the anonymous authentication of sensing vehicles. Besides, even if a sensing vehicle passes anonymous authentication, it is difficult to fully guarantee its reliability. Then, a privacy-preserving reliability evaluation algorithm is adopted to evaluate the reliability of sensing vehicles. Meanwhile, in dynamic vehicular networks, the reliability of sensing vehicles is uncertain since there exist many attacks, thus, an accurate reputation update algorithm is designed. Subsequently, the privacy features, computation, and communication overheads in the proposed scheme are analyzed. Comparisons with the existing schemes show that the authentication efficiency of the proposed scheme is increased by 46%–74%, the communication overhead is reduced by 50%–80%, and the accuracy of reputation values of sensing vehicles which submit the reliable/unreliable sensing data is improved/reduced by 16%–22%/67%–74%.

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.

With the rapid development of the Internet of Vehicles (IoV), location-aware outsourcing data aggregation is evolving into a fundamentally key role for analyzing a significant amount of data among smart devices. Due to the spatial property of the data in IoV, location privacy and data security in outsourcing data aggregation face critical challenges. Meanwhile, because of the diversity of entities in IoV, how aggregating data from multiple domains is also a serious issue. In this article, we propose a location-aware verifiable outsourcing data aggregation (LAVODA) for IoV where aggregators are hierarchical for the cross-chain mechanism in multiblockchains. With homomorphic encryption and homomorphic commitment, we achieve the verifiability of the aggregation while ensuring data confidentiality. Specifically, we combine twin-DH with circle-based location verification to ensure the privacy of the requester’s location strategy and data providers’ locations. The security analysis shows that our scheme can achieve the above secure properties. In addition, the experimental results demonstrate that our scheme is efficient and feasible in practice.

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.

Cloud-Fog-Assisted Internet-of-Things (IoT) is a convincing paradigm to provide users with on-demand and low-latency services through Fog nodes in the edge of multiple clouds (Multi-Cloud). Multi-Cloud is a scalable multi-domain service-oriented net-centric system and can respond to complicated user requirements leveraging Multi-Cloud Service Composition (MCSC). However, in MCSC, user security can be easily compromised by untrusted and curious cloud service providers that may collect and violate the privacy and other essential assets of cloud users. Although many trust-based MCSC solutions have been proposed to seek a trustworthy composite service with highest trust level, most of them are vulnerable to malicious users intending to break through the clouds and inflict serious data leakage or asset damage. Considering these security concerns on both malicious users and untrusted service providers, in this article, we present a trust-based secure multi-cloud collaboration framework for Cloud-Fog-Assisted IoT systems. Specifically, to guarantee the security of users, we develop a role-based trust evaluation method to enhance the trustworthiness of MCSC. To preserve the security of services, we design an efficient user authentication scheme and a secure collaboration scheme to provide collaborative user authentication and access control mechanism for MCSC. We develop a proof of concept implementation for our framework and demonstrate its practicability by performance evaluation with extensive experiments.

Recently, the explosive development of unmanned aerial vehicles (UAVs) promotes its wide application in various services such as package delivery, traffic monitoring. However, due to the high-speed movement, current UAVs usually adopts the unsecure channel without the complicated authentication mechanism to ensure real-time communication. In this paper, we introduce a certificateless authentication scheme with fuzzy batch verification (CLFBV) to achieve once-for-all verification of parallel messages and ensure the real-time secure communication of UAVs. CLBFV defines the error tolerance property for authenticated communication, which allows a tolerance threshold for the messages that are unable to pass authentication. In addition, our proposed scheme is proved to be secure and existentially unforgeable under the chosen message attack and fuzzy identity attack in the random oracle model. The efficiency analysis shows that CLBFV is more efficient and feasible than other existing batch verification schemes.

Cloud-assisted Industrial Internet of Things (IIoT) systems are increasingly deployed in various applications such as location-based services. Outsourcing data to cloud servers can help minimize local data storage and computation overheads, but it may introduce security and privacy concerns. Therefore, privacy-preserving spatial keyword search has been extensively explored in the literature. However, existing solutions still reveal the order of the spatio-textual similarity values between the query point and all data objects, and do not support searching for arbitrary geometric regions. To solve these issues, in this article we propose a privacy-preserving threshold spatial keyword search (TSKS) scheme. Specifically, we use the polynomial fitting technology, vector space model, and randomizable matrix multiplication technology to allow the cloud server to find relevant objects that are within some arbitrary geometric range and contain all query keywords. Finally, formal security analysis proves that our scheme can protect the privacy of data sets and queries, and extensive experiments demonstrate that our scheme is efficient and practical.

In the mobile crowdsensing (MCS) with large-scale data collection and sharing environments, since a growing number of applications need to exploit multisource sensing information, it is almost indispensable to develop a generic mechanism supporting efficient and accurate multiple tasks allocation. Meanwhile, achieving the maximum service benefit, the cloud server allocates the multitask based on the user attribute preferences, but it will lead to the privacy leakage of sensing users (SUs). Motivated by the aforementioned challenges, we propose a privacy-preserving multitask allocation (PMTA) scheme for MCS in this article. Specifically, we exploit$K$-means clustering and matrix multiplication to realize a secure and efficient grouping mechanism, which achieves the selection of high-quality and accurate target users set with privacy preserving. Based on the short group signature algorithm and 0–1 encoding technique, we construct a privacy-preserving matching mechanism to guarantee the anonymous authentication and achieve the matching for task requirements and user reputation levels in a privacy-preserving way. Finally, we give a security analysis, and we evaluate the computational costs and communication overhead, and the experimental result shows the efficiency of our proposed PMTA scheme.

The large amount of driving data can help intelligent vehicles make decisions to drive safely, improve vehicular services and enhance driving experience. In traditional vehicular networks, data sharing needs to be done with roadside units (RSUs). However, RSUs cannot be entirely trusted and the data stored in the RSUs may be tampered with. In addition, the deployment of RSUs along roads consumes a large amount of social resources. Further, data sharing between vehicles lacks a trusted environment, and vehicles may be unwilling to share data with others because of data security and privacy concerns. Moreover, in the event of unauthorized data sharing, the source of the leaked data is difficult to trace. In this study, we exploit consortium blockchain technology to achieve traceable and anonymous vehicle-to-vehicle (V2V) data sharing, effectively preventing second-hand sharing of data. The combination of 5G and blockchain makes it possible to share data without using RSUs. We design an enhanced delegated proof-of-stake consensus algorithm to make it more suitable for applications in the distributed Internet of Vehicles (IoV). A comprehensive analysis shows that the proposed scheme is secure and efficient.

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.

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.

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.

Privacy protection and defense against poisoning attack and are two critical problems hindering the proliferation of federated learning (FL). However, they are two inherently contrary issues. For constructing a privacy-preserving FL, solutions tend to transform the original information (e.g., gradient information) to be indistinguishable. Nevertheless, to defend against poisoning attacks is required to identify the abnormal information via the distinguishability. Therefore, it is really a challenge to handle these two issues simultaneously under a unified framework. In this paper, we build a bridge between them, proposing a scalable privacy-preserving federated learning (SPPFL) against poisoning attacks. To be specific, based on the the technology of secure multi-party computation (MPC), we construct a secure framework to protect users’ privacy during the training process, while punishing poisoners via the method of distance evaluation. Besides, we implement extensive experiments to illustrate the performance of our scheme.

Vehicles gather data collected by sensor nodes, combined with messages obtained from the other nodes in vehicular ad hoc networks (VANETs), to achieve safe driving. An announcement type of message is sent in the VANET; it is collected by mobile vehicles, uploaded to a cloud server for storage, and provided to other vehicles for reference. However, in an open cloud environment, plaintext data are vulnerable to unauthorized access and even malicious tampering. To solve this issue, we propose an attribute-based encryption algorithm using blockchain, which is maintained by a roadside unit (RSU). The uploader's symmetric key is recorded on the blockchain, and all uploaded and accessed transactions are recorded for auditing. Our scheme can achieve the function of securely accessing different types of announcement messages according to different vehicle attributes. Security analysis and experimental results indicate that our scheme has achieved a balance between security and efficiency.

This paper proposes a cost-effective, high-impedance-state (HIS)-insensitive, triple-node-upset (TNU)-tolerant and single-event-transient (SET)-filterable latch, namely HITTSFL, to ensure high reliability with low-cost. The latch mainly comprises an output-level SET-filterable Schmitt-trigger and three inverters that make the values stored in three parallel single-node-upset (SNU)-recoverable dual-interlocked-storage-cells (DICEs) converge at a common node to tolerate any possible TNU. The latch does not use C-elements to be insensitive to the HIS. Simulation results demonstrate the TNU-tolerability and SET-filterability of the proposed HITTSFL latch. Moreover, due to the use of clock-gating technologies and fewer transistors, the proposed latch can reduce delay, power, and area by 76.65%, 6.16%, and 28.55%, respectively, compared with the state-of-the-art TNU hardened latch (TNUHL) that cannot filter SETs.

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.

This paper presents a novel dual-interlocked storage-cell (DICE)-based double-node-upset (DNU) self-recoverable, namely DURI-FF, in the nano-scale CMOS technology. The master latch of the DURI-FF cell consists of three transmission gates (TGs) and three interlocked DICEs with three common nodes. The common nodes are connected to TGs for value initialization. The slave latch of the DURI-FF cell comprises six TGs, six inverters and three interlocked DICEs. The outputs of the inverters respectively feed the internal nodes of the slave latch. The interlocked DICEs make the master latch and the slave latch DNU self-recoverable. Simulation results validate the DNU self-recoverability of the proposed DURI-FF cell. Moreover, compared with the state-of-the-art hardened flip-flop cells, the proposed DURI-FF cell achieves roughly 43% delay reduction at the cost of moderate silicon area and power dissipation.

Autonomous vehicle platoon is a promising paradigm towards traffic congestion problems in the intelligent transportation system. However, under certain circumstances, the advantage of the platoon cannot be fully developed. In this paper, we focus on the highway Electronic Toll Collection (ETC) charging problem. We try to let the opportunistic platoon pass the ETC as a whole. There are three main issues in this scenario. Firstly, the opportunistic platoon is temporarily composed; vehicles do not trust each other. Secondly, single vehicle may try to escape from the ETC charging by following the platoon. Finally, platoon members may collude with each other and try to underreport the number of vehicles in the platoon so as to evade payment. To solve these challenges, we propose a blockchain-based efficient highway toll paradigm for the opportunistic platoon. The driving history, credential information of every registered vehicle, is recorded and verified from the blockchain. A roadside unit (RSU) is adopted to distinguish the single vehicle from the platoon and in charge of lane allocation. Additionally, an aggregate signature is introduced to accelerate the authentication procedure in the RSU. We analyse the potential security threats in this scenario. The experimental result indicates that our scheme is efficient and practical.

To meet the requirements of both cost-effectiveness and high reliability for safety-critical terrestrial applications, this paper proposes a novel radiation hardened latch design, namely HLCRT. The HLCRT latch mainly consists of a single-node-upset self-recoverable cell, a 3-input C-element, and an inverter. If any two inputs of the C-element suffer from a double-node-upset (DNU), or if one node inside the cell together with another node outside the cell suffer from a DNU, the latch still has correct values on its output node, i.e., the latch is effectively DNU hardened. Simulation results demonstrate the DNU tolerance of the proposed latch. Moreover, due to the use of fewer transistors, clock gating technologies, and a high-speed path, the proposed latch saves about 444.80% delay, 150.50% power, 72.66% area, and 2029.63% delay-power-area product on average, compared with state-of-the-art DNU hardened latch designs.

The Aggressive technology scaling makes modern advanced SRAMs more and more sensitive to soft errors that include single-node upsets (SNUs) and double-node upsets (DNUs). This paper presents a novel Sextuple Cross-Coupled SRAM cell, namely SCCS cell, which can tolerate both SNUs and DNUs. The cell mainly consists of six cross-coupled input-split inverters, constructing a large error-interceptive feedback loop to robustly retain stored values. Since the cell has many redundant storage nodes, the cell achieves the following robustness: (1) the cell can self-recover from all possible SNU; (2) the cell can self-recover from partial DNUs; (3) the cell can avoid the occurrence of other DNUs due to node-separation. Simulation results validate the excellent robustness of the proposed cell. Moreover, compared with the state-of-the-art typical existing hardened cells, the proposed cell achieves an approximate 61% read access time as well as 12% write access time reduction at the costs of 47% power dissipation as well as 44% silicon area on average.

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.

Traditional public key infrastructure-based authentication schemes provide vehicular networks with identity authentication and conditional privacy protection, which are not sufficient for assessing the credibility of messages. Additionally, although the new generation of cellular networks (5G) can dramatically improve the transmission efficiency of the messages, many existing authentication schemes are based on complex bilinear pairing operations, and the calculation time is too long to be suitable for delay-sensitive 5G-enabled vehicular networks. To address these issues, we propose a reputation system-based lightweight message authentication framework and protocol for 5G-enabled vehicular networks. The trusted authority (TA) is in charge of reputation management. A vehicle with a reputation score below the given threshold cannot obtain a credit reference from the TA for participating in the communication; therefore, the number of untrusted messages in vehicular networks is reduced from the source. Security analysis shows that our scheme is secure against an adaptively chosen-message attack, and also satisfies a series of requirements of vehicular networks. The scheme is based on the elliptic curve cryptosystem and supports batch authentication; therefore, it shows better performance in terms of time consumption when compared with related schemes.

In cloud‐assisted electronic health care (eHealth) systems, a patient can enforce access control on his/her personal health information (PHI) in a cryptographic way by employing ciphertext‐policy attribute‐based encryption (CP‐ABE) mechanism. There are two features worthy of consideration in real eHealth applications. On the one hand, although the outsourced decryption technique can significantly reduce the decryption cost of a physician, the correctness of the returned result should be guaranteed. On the other hand, the malicious physician who leaks the private key intentionally should be caught. Existing systems mostly aim to provide only one of the above properties. In this work, we present a verifiable and traceable CP‐ABE scheme (VTCP‐ABE) in eHealth cloud, which simultaneously supports the properties of verifiable outsourced decryption and white‐box traceability without compromising the physician’s identity privacy. An authorized physician can obtain an ElGamal‐type partial decrypted ciphertext (PDC) element of original ciphertext from the eHealth cloud decryption server (CDS) and then verify the correctness of returned PDC. Moreover, the illegal behaviour of malicious physician can be precisely (white‐box) traced. We further exploit a delegation method to help the resource‐limited physician authorize someone else to interact with the CDS. The formal security proof and extensive simulations illustrate that our VTCP‐ABE scheme is secure, efficient, and practical.