With the deepening of the Internet of Things (IOT) and industrial digital transformation, the core of positioning services is shifting from “serving people” to “connecting everything”, which poses a comprehensive challenge to indoor positioning technology in terms of high accuracy, low latency, low power consumption, and low cost. Traditional radio frequency positioning technology has shown many limitations in this context, while visible light positioning (VLP) technology has become a highly promising supplementary solution due to its unique advantages, such as the absence of authorized spectrum, no electromagnetic interference, high security, and the ability to balance lighting. However, traditional VLP methods heavily rely on accurate channel models and are difficult to cope with complex non-line-of-sight environments, resulting in increasingly prominent performance bottlenecks. In recent years, the rapid development of machine learning technology has provided a new paradigm for solving the above-mentioned problems. From the perspective of the IOT and edge computing, this paper systematically summarizes the latest progress of how machine learning can improve the performance of indoor VLP.We first elaborate on the architecture and basic principles of edge-oriented VLP systems. Then, a comprehensive review and comparison are performed on VLP methods based on traditional machine learning and deep learning. Moving on, we provide the analysis on how they improve system accuracy and robustness through data-driven approaches. Moreover, this article delves into the application and value of different learning paradigms, such as centralized learning, online learning, and federated learning in VLP systems. In addition, we have developed a multi-dimensional evaluation system that includes core positioning accuracy and edge performance indicators to comprehensively measure the feasibility of the system in practical deployment. Finally, we present the identified challenges and future research directions in this under-explored field from aspects of standardized scenario modeling, high generalization base models, dynamic environment robustness, heterogeneous terminal adaptation, and edge lightweight models.

Federated Learning (FL) offers a privacy-preserving framework for training audio classification (AC) models across decentralized clients without sharing raw data. However, Federated Audio Classification faces three major challenges: data heterogeneity , model heterogeneity , and data corruption , which degrade performance in real-world settings. While existing methods often address these issues separately, a unified solution remains underexplored. We propose FedMLAC, a mutual learning-based FL framework that tackles all three challenges simultaneously. Each client maintains a personalized local AC model and a lightweight, globally shared Plug-in model. These models interact via bidirectional knowledge distillation, enabling global knowledge sharing while adapting to local data distributions, thus addressing both data and model heterogeneity. To counter data corruption, we introduce a Layer-wise Pruning Aggregation (LPA) strategy that filters anomalous Plug-in updates based on parameter deviations during aggregation. Extensive experiments on four diverse AC benchmarks, including both speech and non-speech tasks, show that FedMLAC consistently outperforms state-of-the-art baselines in classification accuracy and robustness to noisy data.

Australia harbours a rich and unique diversity of wildlife, constituting a vital component of the nation’s ecological heritage. Accurate species identification in expansive and remote natural environments remains a significant challenge. In this study, we propose YOLO-Feature and Clustering Enhanced (YOLO-FCE), an improved model based on the YOLOv9 architecture. We conducted a series of cluster-distance-based analyses to evaluate and enhance the model’s feature extraction capabilities. The proposed model was trained and tested on a dataset containing 50 Australian animal species, with 700 images per species, resulting in a total of 35,000 images. YOLO-FCE achieved a mean Average Precision (mAP50:95) of 87.5% and a precision of 98.2%. On a separate validation set of previously unseen images, it attained a recognition accuracy of 91.29% with an average confidence score of 0.801. Compared with baseline models including YOLOv9, YOLOv11, and Faster R-CNN evaluated on the same dataset, YOLO-FCE demonstrated robust performance.

Federated Learning (FL), an innovative distributed paradigm, has attracted significant interest for its inherent privacy preservation in collaborative model training. However, recent studies demonstrate that publicly shared gradients are vulnerable to malicious reconstruction of sensitive client data. While countermeasures like differential privacy and homomorphic encryption exist, they typically compromise model accuracy or computational efficiency, hindering practical deployment. This work simultaneously addresses two critical challenges in the FL training process: 1) efficient protection of client privacy, and 2) guaranteeing the authenticity of client gradients while ensuring the verifiability of the server's aggregation result. To this end, we propose an efficient and authentication-enhanced privacy-preserving protocol. Our solution allows clients to mask their local gradients and furnish corresponding proofs. The aggregation server subsequently verifies all submissions, aggregates only the valid masked gradients, and generates a proof for clients to verify the correctness of the aggregation result. Furthermore, the protocol is designed to be robust against client dropout. We provide formal proof that our protocol meets all security requirements in a semi-trusted environment. Both comprehensive theoretical analysis and extensive experimental evaluations confirm that our approach achieves more robust security, better dropout resilience, and superior overall efficiency compared to state-of-the-art protocols such as PSA, VerifyNet, and EVP.

MobileEdgeComputing (MEC) has incentivized App vendors to outsource various services and applications to distributed edge nodes for low access latency. However, the data cached on these nodes is vulnerable to both intentional and accidental corruption, necessitating periodic audits ofEdgeDataIntegrity (EDI). Existing solutions either rely on a “fully trustworthy”ThirdPartyAuditor (TPA) or leverage blockchain to enhance trust. However, they overlook the security risks brought by the use of blockchain, particularly collusion attacks. Furthermore, while they employ achallenge-responsemechanism to enhance efficiency by batch verification, they fail to account for the heterogeneity of edge nodes. To address these challenges, we propose$\mathtt {CTCV}$, aCollusion-resistant andTime-awareCollaborativeVerification framework.$\mathtt {CTCV}$aims to accommodate edge node heterogeneity while enabling public audits and batch verification without introducing additional security risks. Specifically, it incorporates blockchain to allow edge nodes to collaboratively verify EDI without trust dependencies, while mitigating collusion attacks through a carefully designed proof generation and verification approach. Considering the resource and state heterogeneity of edge nodes,$\mathtt {CTCV}$employs atime-constrained challenge-responsemechanism that sets a time threshold$\mathcal {T}$between the verification request issuance and the integrity proof inspection to avoid excessive delays. The selection guideline of$\mathcal {T}$, along with the correctness, efficiency, and collusion resistance of$\mathtt {CTCV}$, are rigorously analyzed. Extensive experiments validate that$\mathtt {CTCV}$is computationally and communicationally efficient compared to three baselines: EdgeWatch, EDI-S, and EDI-V. On average, given 10 edge nodes,$\mathtt {CTCV}$outperforms EdgeWatch, EDI-S, and EDI-V with computation efficiency improvements of 7.9, 9.0, and 5.0 times, and communication efficiency improvement of 2063.0, 4.8, and 2.6 times, respectively.

Multiplex graphs represent diverse real-world interactions among entities, where multiple relationship types coexist within the same set of entities. These graphs introduce privacy risks, as data collectors can exploit cross-layer dependencies to infer hidden and sensitive connections. In this work, we propose aC2P-Mframework that identifies and protects critical connections while preserving the structural information in multiplex graphs. Unlike conventional methods for single-layer graphs that perturb all edges uniformly,C2P-Mselectively protects critical connections, maintaining the analytical usability of the graph. To achieve this, we introduce the multiplex$p$-cohesion model, which incorporates new score functions that account for both intra-layer and inter-layer dependencies, enabling precise identification of critical connections for each vertex. For privacy protection, our method protects the identified critical connections, leveraging an adaptive Randomized Response (RR) mechanism to ensure$\varepsilon$-Local Differential Privacy (LDP). We formally prove thatC2P-Msatisfies$\varepsilon$-LDP. Extensive experiments on eight real-world multiplex graph datasets demonstrate thatC2P-Msignificantly outperforms baseline privacy-preserving methods, achieving a better privacy-utility trade-off.

With the emergence of fluid antenna (FA) in wireless communications, the capability to dynamically adjust port positions offers substantial benefits in spatial diversity and spectrum efficiency, which are particularly valuable for mobile edge computing (MEC) systems. Therefore, we propose an FA-assisted MEC offloading framework to minimize system delay. This framework faces two severe challenges, which are the complexity of channel estimation due to dynamic port configuration and the inherent non-convexity of the joint optimization problem. Firstly, we propose Information Bottleneck Metric-enhanced Channel Compressed Sensing (IBM-CCS), which advances FA channel estimation by integrating information relevance into the sensing process and capturing key features of FA channels effectively. Secondly, to address the non-convex and high-dimensional optimization problem in FA-assisted MEC systems, which includes FA port selection, beamforming, power control, and resource allocation, we propose a game theory-assisted Hierarchical Twin-Dueling Multi-agent Algorithm (HiTDMA) based offloading scheme, where the hierarchical structure effectively decouples and coordinates the optimization tasks between the user side and the base station side. Crucially, the game theory effectively reduces the dimensionality of power control variables, allowing deep reinforcement learning (DRL) agents to achieve improved optimization efficiency. Numerical results confirm that the proposed scheme significantly reduces system delay and enhances offloading performance, outperforming benchmarks. Additionally, the IBM-CCS channel estimation demonstrates superior accuracy and robustness under varying port densities, contributing to efficient communication under imperfect CSI.

With the rise of the smart industry, machine learning (ML) has become a popular method to improve the security of the Industrial Internet of Things (IIoT) by training anomaly detection models. Federated learning (FL) is a distributed ML scheme that facilitates anomaly detection on IIoT by preserving data privacy and breaking data silos. However, poisoning attacks pose significant threats to FL, where adversaries upload poisoned local models to the aggregation server, thereby degrading model accuracy. The prevalence of non-independent and identically distributed (non-IID) data across IIoT devices further exacerbates this threat, as it naturally leads to diverse local models, making malicious ones harder to distinguish. To address the above challenges, we propose a deep-layer sign-sharing personalized FL (DSPFL) scheme. DSPFL innovatively aggregates only the signs of stochastic gradients (SignSGD) from the deep layers of local models during training. This targeted aggregation enhances the robustness of the shared components against poisoning attacks, while shallow layers are retained locally to preserve personalization. This integrated approach improves the accuracy and resilience of personalized local models on IIoT devices under poisoning attacks. Extensive experimental results show that DSPFL consistently achieves up to 20% higher and more stable overall personalized model accuracy compared to state-of-the-art methods under specific poisoning attacks.

With the exponential surge in media data volumes and their growing intrinsic value, the landscape has become increasingly susceptible to persistent and strategically designed data poisoning attacks targeting these valuable assets. In this work, we propose a novel approach leveraging generative AI techniques to craft covert and robust poisonous data samples, referred to as Chimera Images. These images seamlessly blend visual features from two target classes to generate hybrid objects that preserve appearance fidelity. These ''normal'' samples with correct labels can subtly distort the model's decision boundary without raising suspicion. Extensive experimental results on CIFAR-10 and Flowers datasets demonstrate that the proposed method i) reduces the accuracy of the targeted class, ii) maintains the performance of other classes, and iii) exhibits immunity to state-of-the-art defence strategies. We also explore the usage of generative AI content detection as a defence mechanism, demonstrating that the recently discovered snapshot technique is ineffective against the AI-generated poisonous Chimera samples.

Phishing emails increasingly embed complex social engineering (SE) tactics to manipulate recipients and increase success rates. However, existing organizational training simulations and detection systems seldom incorporate tactic complexity or reveal how such tactics are linguistically embedded. To address this, we develop methods for generating, annotating, and evaluating SE tactics across three complexity levels in phishing emails. A reliably annotated dataset is constructed via a generate–cross-verify–highlight pipeline, which ensures semantic alignment between labels and embedded SE tactics. These trigger segments are subsequently clustered and synthesized into fine-grained patterns that characterize how each SE tactic manifests at Level 1 (easily), Level 2 (moderately), and Level 3 (deeply). These patterns underpin a multi-level SE framework, validated through LLM-based detection experiments. Detection accuracy declines with increasing tactic complexity, confirming the framework's stratification capability and its utility in training, simulation, and tactic-aware detection design.

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in visual-language understanding for downstream multimodal tasks. However, these models often generate descriptions containing objects or details not present in the input image, a phenomenon commonly referred to as ''hallucination''. Existing methods focus solely on single-side hallucination mitigation: Intra-modal-only reinforcement (e.g. visual attention enhancement) ignores prompt-based guidance; Inter-modal-only correlation correction may introduce low-information visual tokens to mislead reasoning. To tackle this challenge, we propose Dual-Modal Collaborative Attention Reinforcement (DuCAR). Specifically, DuCAR is equipped with intra-visual CLS-driven sampling and cross-modal dynamic sampling, extracting important visual tokens guided by intra- and inter-modal joint information. During the multimodal fusion stage, DuCAR adaptively enhances the attention weights of these visual tokens. Our sampling and enhancement strategies in DuCAR simultaneously reinforces informative visual tokens, and suppresses attention dispersion towards question-irrelevant visual information. We conduct extensive experiments on the POPE and CHAIR hallucination benchmarks, demonstrating that our method outperforms existing state-of-the-art mitigation baselines and effectively reduces hallucinations in text generated by LVLMs. The code is available in the https://github.com/xjy2020/DuCAR.

The increase in computing power and the necessity of AI-assisted decision-making boost the growing application of large language models (LLMs). Along with this, the potential retention of sensitive data of LLMs has spurred increasing research into machine unlearning. However, existing unlearning approaches face a critical dilemma: Aggressive unlearning compromises model utility, while conservative strategies preserve utility but risk hallucinated responses. This significantly limits LLMs' reliability in knowledge-intensive applications. To address this, we introduce a novel Attention-Shifting (AS) framework for selective unlearning. AS is driven by two design objectives: (1) context-preserving suppression that attenuates attention to fact-bearing tokens without disrupting LLMs' linguistic structure; and (2) hallucination-resistant response shaping that discourages fabricated completions when queried about unlearning content. AS realizes these objectives through two attention-level interventions, which are importance-aware suppression applied to the unlearning set to reduce reliance on memorized knowledge and attention-guided retention enhancement that reinforces attention toward semantically essential tokens in the retained dataset to mitigate unintended degradation. These two components are jointly optimized via a dual-loss objective, which forms a soft boundary that localizes unlearning while preserving unrelated knowledge under representation superposition. Experimental results show that AS improves performance preservation over the state-of-the-art unlearning methods, achieving up to 15\% higher accuracy on the ToFU benchmark and 10\% on the TDEC benchmark, while maintaining competitive hallucination-free unlearning effectiveness. Compared to existing methods, AS demonstrates a superior balance between unlearning effectiveness, generalization, and response reliability.

To enhance service quality, wireless computing power networks (WCPNs) need to realize flexible scheduling and allocation of computation resources across heterogeneous computing servers. Due to large user scales and diverse computation tasks, it is difficult for the current WCPN to serve multiple users and handle multiple tasks concurrently. Graph learning is a promising approach that can learn the representations of nodes through graph structures, enabling the exploration of dependencies among multiple users and tasks, and thereby facilitating computation task offloading. In this paper, we propose a graph learning-based multi-user multi-task offloading scheme for WCPN. First, we propose a wireless computing power network with multi-user and multi-task in which users need to make full use of distributed computing resources through task offloading to ensure efficient task execution. We formulate a system energy consumption minimization problem to jointly optimize computation resources, transmission power, and task offloading. To address the problem, we utilize graph learning to transform the joint optimization problem into a graph regression problem and leverage line graph to explore the solution. Numerical results demonstrate that our proposed scheme can improve computation efficiency, enhance optimization performance, and maintain transferability compared with the benchmarks.

With the rapid development of big data, Federated learning (FL) has found numerous applications, enabling machine learning (ML) on edge devices while preserving privacy. However, FL still faces crucial challenges, such as single point of failure and poisoning attacks, which motivate the integration of blockchain-enabled FL (BeFL). Beyond that, the efficiency issue still limits the further application of BeFL. To address these issues, we propose a novel decentralized framework: Accelerating Blockchain-Enabled Federated Learning with Clustered Clients (ABFLCC), who utilize actual training time for clustering clients to achieve hierarchical FL and solve the single point of failure problem through blockchain. Additionally, the framework clusters edge devices considering their actual training times, which allows for synchronous FL within clusters and asynchronous FL across clusters simultaneously. This approach guarantees that devices with a similar training time have a consistent global model version, improving the stability of the converging process, while the asynchronous learning between clusters enhances the efficiency of convergence. The proposed framework is evaluated through simulations on three real-world public datasets, demonstrating a training efficiency improvement of 30% to 70% in terms of convergence time compared to existing BeFL systems.

With the advancement of Mobile Edge Computing (MEC), App vendors are increasingly motivated to cache multiple data replicas on geographically distributed edge servers to ensure rapid responses for latency-sensitive applications. However, the security of data replicas is a critical concern due to the dynamic nature and resource limitations of MEC environments. To this end, data replicas’ integrity must be regularly verified to maintain the accuracy of data-driven decision-making. Existing Edge Data Integrity (EDI) verification solutions suffer from low efficiency due to relying on indiscriminative verification, where all data replicas are checked at each round without considering their inherent reliability characteristics. This paper designs an Intelligent framework called I-EDI, which enables discriminative EDI verification by integrating a novel Long-term Unreliable data Replica Selection (L-URS) mechanism. This framework aims to reduce verification costs without compromising accuracy, while resisting spoofing, forgery, outsourcing, collusion, alteration-before-verification, delayed-response, and adaptive attacks. Specifically, each data replica is associated with a reliability representation by evaluating its long-term performance. Based on that, the L-URS problem is defined as stochastically minimizing the global reliability representation over time, subject to constraints on the number of data replicas to be verified. To make it easy-to-handle, the L-URS problem is decomposed into a series of online minimization problems. An Online Opportunistic-based Replica Selection approach called O2RS is developed. O2RS allows App vendors to significantly decrease verification costs by targetedly inspecting unreliable data replicas. Moreover, this work provides a thorough theoretical analysis of O2RS’s time complexity and approximation bound, as well as I-EDI’s security. Extensive experiments are conducted to validate the effectiveness and efficiency of O2RS and I-EDI. The results demonstrate that, compared to commonly used alternatives, O2RS achieves an approximate 50% improvement in selection efficiency, while I-EDI reduces verification costs by 1.23 times on average.

Edge storage has become a widely used solution for providing low-latency data access services, which motivates data owners to outsource data on geographically distributed edge nodes to deliver a positive user experience. Nevertheless, various security concerns raise in terms of data availability. Among them, edge data geo-location verification becomes a prominent concern when the data is out of owners' control, since outsourced data may be re-outsourced to other economical yet unknown third-party devices by dishonest edge nodes for saving storage space and pocketing the difference. Existing geo-localization approaches for cloud architectures can not be practically applied to identify such re-outsourcing behaviors due to the uniqueness of edge storage. To close this gap, we make the first attempt to investigate theedgedatare-outsourcingdetection (EDRD) problem, enabling the data owner to inspect if outsourced data is consistently cached on the rented edge nodes with agreed geo-location. We leverage timedChallenge-Responsemechanisms for data possession proof while measuring verification latency to detect re-outsourcing behaviors by comparing with re-outsourcing detection threshold$\mathbb {C}$. We prove that the edge node whose verification latency exceeds$\mathbb {C}$is dishonest. To obtain the optimal$\mathbb {C}$, we formulate thethresholddetermination (TD) problem and transform it to an easy-to-handle form for problem complexity reduction. Then, apreference-based approach named TD-P is developed to efficiently address the transformed TD problem. On top of that, we propose a$\mathbb {C}$-aware edge data re-outsourcing detection scheme entitled EDRD-$\mathbb {C}$to tackle the EDRD problem effectively. The efficiency and effectiveness of TD-P and EDRD-$\mathbb {C}$are verified by extensive theoretical analysis and experimental evaluations on both simulated and real platforms. Notably, EDRD-$\mathbb {C}$achieves 100% detection accuracy by sacrificing a reasonable amount of computing resources and 92.97% in the worst case.

Federated learning (FL) has been widely applied in medical field, which allows clients to collaboratively train global models without sharing local data. Nevertheless, the diversity and scarcity of samples from rare diseases may result in a decline in the performance of local models on client-side due to using a singular global model. Moreover, direct transmission of local models or parameters will likely lead to user privacy violations. To solve these problems, we propose a Grouped Federated Meta-Learning (GrFML) method to improve the performance of local personalization models while protecting data privacy. Specifically, we first utilize a self-attention mechanism to extract partial features from the client’s local data, which are uploaded to the server (medical data is susceptible to perturbation and data integrity, thus this process does not expose the private data). The server groups clients with similar features based on these extracted features. Then, multiple meta-models are trained on these groups and distributed back to the clients to enhance the performance of the client’s local models. Furthermore, during the FL process, we introduce dynamic perturbation to the uploaded gradients based on the model’s test accuracy to protect their privacy. Typically, the perturbation magnitude is directly proportional to the model’s test accuracy. Extensive experiments shown that the GrFML model significantly improves client personalization model accuracy and achieves a good privacy-utility trade-off.

Decentralized Federated Learning (DFL) is extensively applied in various areas, e.g., healthcare, finance, and Internet of Things (loT), offering practical solutions for distributed intelligent applications and data collaboration. In DFL systems, participants, e.g., edge devices, organizations, or nodes, collaborate in the training of a shared global model by aggregating local models from various participants. During this process, participants need to communicate frequently with a central authority/node/server to share model parameters. Such communication is vulnerable to malicious attacks or tampering, posing a significant threat to the integrity of model training. The integrity verification method can provide an integrity guarantee for the global model of DFL. However, most of the existing integrity verification schemes are centralized and not suitable for resource-constrained DFL scenarios. Therefore, how to verify the integrity of the global model becomes an important issue in DFL. To address it, we devise a global model integrity verification method for DFL. Specifically, we generate a digital signature for each global model parameter as proof of integrity, while improving the efficiency of integrity verification by electing delegates to conduct the verification process. A series of experiments is conducted to validate the performance of the proposed method. The experimental results demonstrate that our approach not only effectively ensures the integrity of the global model but also functions well under limited resources.

Note:This paper contains many malicious contents generated by LLMs. Jailbreak can cause large language models (LLMs) to violate moral and ethical guidelines, generating harmful text and images. However, the existing jailbreaks are high-cost (e.g., fine-tuning LLMs) and underperform when facing some specific jailbreak tasks (e.g., generating pornographic and bloody texts), which has too many limitations for reflecting the threat of jailbreak on LLMs’ security. To fill this gap, in this paper, we propose a black-box jailbreak with a higher attack success rate and lower cost, called Dictionary Jailbreak with Multi-round Induction (DJMI). First, in DJMI, we create a simple custom language dictionary based on specific jailbreak tasks to be performed and send it to the LLM. Then, we use the custom language from the dictionary to construct malicious prompts, instructing the LLM to respond in the custom language as much as possible. Generally, in the first round, the LLM will provide a neutral response (such as translating the malicious prompts) or refuse to answer. To counteract this, we need to emphasize that the prompts comply with ethical guidelines and repeat the prompts using the custom language. The process can be conducted with multiple rounds to guide LLM in outputting harmful content. During the attack process, the only attack cost is the transmission cost of the prompts through the official interactive interface, without any other costs of LLM fine-tuning, algorithm design and prompt generation. Thus, DJMI is a low-cost jailbreak method. We verified DJMI on multiple mainstream LLMs across various jailbreak tasks. Experiments show that compared to existing black-box jailbreaks, DJMI achieves a higher attack success rate (> 80% on average) across specific jailbreak tasks with various risk levels. Additionally, DJMI enables the LLM to provide highly detailed execution steps for harmful behaviors within a session (such as specifying proportions of ingredients, synthetic chemical formulas, experimental conditions, and other detailed information in illicit drug production), further highlighting the severity of jailbreak attacks.

The consortium blockchain is being utilized in supply chains on the Internet of Things (IoT) for tracking and protecting supply chain data, such as manufacture, storage, and shipment. However, the supply chain data in a consortium blockchain is publicly accessible for all parties, which attracts widespread concerns about supply chain data privacy. Several existing attribute-based encryption (ABE)-based blockchain systems targeting to address the supply chain data privacy problem either bring about additional security problems or lack the feasibility analysis on IoTs. To address the aforementioned issues, in this article, a novel multiauthority ABE (MA-ABE)-based blockchain system is proposed to protect the data privacy for the supply chain on IoTs. Specifically, a four-way tradeoff optimization framework is designed so that the system decentralization, scalability, and storage consumption are not significantly affected by the improved privacy. The optimal attribute setting policies for different scale blockchain networks are dynamically generated by the nondominated sorting genetic algorithm II (NSGA-II). Extensive experiment results show that the proposed scheme remarkably improves data privacy protection for the supply chain without downgrading the other three key factors.

Edge intelligence, an emerging distributed paradigm, is driven by the increasing number of Internet of Things devices and the development of edge computing and artificial intelligence. This paradigm revolutionizes the way of data caching by encouraging latency-sensitive data to be distributed across multiple edge nodes. In such data caching scenarios, ensuring the integrity of data stored at the edge nodes is critical for business continuity guarantee. Existing Edge Data Integrity (EDI) verification solutions rely on the interactive Challenge-Response mechanism. However, this mechanism imposes significant communication overhead on participants, leading to low verification efficiency. To address this challenge, we propose a Learning-based Hierarchical Edge Data Corruption Detection framework (LH-EDCD), aiming to enhance verification efficiency from a round perspective by reducing communication interaction between edge nodes and the data owner. LH-EDCD involves two layers of verification: internal and external. In the internal verification layer, each edge node self-inspects the cached data replica by running a corruption detection model distributedly trained by blockchain-based Federated Learning (FL). With such filtration, potential corruption can be efficiently identified without complex interaction. Considering the false positive existence in the model, in the external verification layer, LH-EDCD adopts a smart contract in blockchain to verify identified potentially corrupted data replicas for corruption confirmation, mitigating the trust concerns among edge nodes while reducing communication overhead on backbone networks. With the combination of these two layers, the overall EDI verification efficiency can be improved by reducing interaction verification time. Additionally, we make the first attempt to investigate the optimal verification time to improve the applicability and practicality of LH-EDCD. Extensive experimental results substantiate the advantages of employing FL in the first layer of LH-EDCD and demonstrate that LH-EDCD outperforms two state-of-the-art EDI approaches, i.e., EDI-S and EDI-V. Specifically, LH-EDCD achieves better model accuracy and convergence speed compared to centralized training, while exhibiting superior efficiency over EDI-S and EDI-V with 3.5 and 2.8 times performance improvements, respectively.

Supported by cloud computing,FederatedLearning (FL) has experienced rapid advancement, as a promising technique to motivate clients to collaboratively train models without sharing local data. To improve the security and fairness of FL implementation, numerousBlockchain-empoweredFederatedLearning (BFL) frameworks have emerged accordingly. Among them, consensus algorithms play a pivotal role in determining the scalability, security, and consistency of BFL systems. Existing consensus solutions to block producer selection and reward allocation either focus on well-resourced scenarios or accommodate BFL based on clients' contributions to model training. However, these approaches limit consensus efficiency and undermine reward fairness, due to involving intricate consensus processes, disregarding clients' contributions during blockchain consensus, and failing to address lazy client problems (malicious clients plagiarizing local model updates from others to reap rewards). Given the aforementioned challenges, we make the first attempt to design a joint solution for efficient consensus and fair reward allocation in heterogeneous BFL systems with lazy clients. Specifically, we introduce a generalizable BFL workflow that can address lazy client problems well. Based on it, the global contribution of BFL clients is decoupled into five dominant metrics, and the block producer selection problem is formulated as a reward-constraint contribution maximization problem. By addressing this problem, the optimal block producer that maximizes global contribution can be identified to orchestrate consensus processes, and rewards are distributed to clients in proportion to their respective global contributions. To achieve it, we develop aContext-awareProof-of-Contribution consensus algorithm named CPoC to reach consensus and incentive simultaneously, followed by theoretical analysis of lazy client problems and privacy issues. Empirical results on widely-used datasets demonstrate the effectiveness of our design in improving consensus efficiency and maximizing global contribution.

Many real-world interconnections among entities can be characterized as graphs. Collecting local graph information with balanced privacy and data utility has garnered notable interest recently. This paper delves into the problem of identifying and protecting critical information of entity connections for individual participants in a graph based on cohesive subgraph searches. This problem has not been addressed in the literature. To address the problem, we propose to extract the critical connections of a queried vertex using a fortress-like cohesive subgraph model known as$p$-cohesion. A user's connections within a fortress are obfuscated when being released, to protect critical information about the user. Novel merit and penalty score functions are designed to measure each participant's critical connections in the minimal$p$-cohesion., facilitating effective identification of the connections. We further propose to preserve the privacy of a vertex enquired by only protecting its critical connections when responding to queries raised by data collectors. We prove that, under the decentralized differential privacy (DDP) mechanism, one's response satisfies$(\varepsilon , \delta )$-DDP when its critical connections are protected while the rest remains unperturbed. The effectiveness of our proposed method is demonstrated through extensive experiments on real-life graph datasets.

The rapid development of technology such as virtual reality and augmented reality, coupled with the reduced direct contact due to the COVID-19 pandemic, has led to the emergence of a more advanced mode of interaction: air handwriting. This new form of human-computer interaction allows users to input text by writing in the air freely. However, deploying and applying existing air handwriting recognition systems in real-world scenarios still presents challenges, particularly in real-time performance, privacy protection, and label scarcity. To address these challenges, we propose a federated active learning framework called FedAWR for air handwriting recognition tasks. FedAWR utilizes distributed learning to train a shared global model in the cloud from multiple user devices at the network's edge, while keeping the user's handwritten data local to ensure privacy. In addition, FedAWR employs an interactive active learning strategy to collect user-provided annotations for iterative training during the online federated learning process, bootstrapping personalized models for each client. To further enhance interactivity and real-time performance, we designed a lightweight recognition model, which is integrated into FedAWR. Finally, extensive experiments were conducted on real-world air handwritten datasets to validate the superiority of FedAWR.

The emergingMobileEdgeComputing (MEC) paradigm reforms the way of data caching by motivating App vendors to store latency-sensitive data on distributed edge servers. In volatile MEC environments, ensuringEdgeDataIntegrity (EDI) is a major concern for App vendors. Existing EDI solutions only consider the scenario with a single App vendor and multiple edge servers, neglecting more complex multi-vendor and multi-server cases. If multiple App vendors check their data replicas cached on the same edge server simultaneously, integrity verification efficiency will drop exponentially. To mitigate this challenge, we make the first attempt to develop aSmartInspectionAlgorithm (SIA) to pre-select unreliable data replicas for different App vendors in each verification round by jointly considering cache services' QoS (Quality-of-Service) and data replicas' unverified time. By implementing this approach, edge servers can merely verify the selected data replicas, greatly reducing computation and communication overheads in EDI verification. Theoretically, SIA can achieve$\mathcal {O}(n)$expected time complexity. Supported by SIA, we expand the EDI problem in multi-vendor and multi-server MEC environments (referred to as the MVMS-EDI problem) and propose a smart contract-based approach entitled MVMS-SC to tackle the problem efficiently and impartially. We provide a rigorous theoretical analysis of the correctness, security, and efficiency of MVMS-SC. Both large-scale and small-scale experiments with real-world datasets are correspondingly performed on a single machine and a real platform to validate the superiority of MVMS-SC in terms of computation and communication efficiencies.

EdgeIntelligence (EI), a burgeoning research area, motivates App vendors to cache data replicas on geographically distributed edge servers to deliver better services. On the downside, this benefit also incurs more data integrity audit overhead on App vendors, which calls for more efficientEdgeDataIntegrity (EDI) verification approaches. However, existing EDI solutions totally rely on an implicitresource homogeneity assumption-edge servers have identical resource availability throughout EDI inspection execution in each round-but it rarely holds in reality. The edge servers with insufficient computation and/or communication capacity greatly limit overall EDI verification efficiency from a round perspective. Thus, in this work, we release the identified impractical assumption and accordingly study the EDIDynamicVerificationAssignment (DVA) problem for the first time. The problem aims to maximize the number of data replicas being verified in the long term under the constraints of verification delay in resource-limited environments. In this way, App vendors merely need to check the integrity of selected data replicas in each round for efficiency improvement. Specifically, we first formalize the DVA problem as a delay-constrained long-term stochastic optimization problem and further prove its$\mathcal {NP}$-hardness. To resolve the problem efficiently, we decompose it to an easy-to-handle form and then develop a polynomial-timePriority-based approach named DVA-P with a theoretical analysis of its time complexity and performance bound. Finally, experimental evaluations validate that DVA-P can be seamlessly incorporated into existing EDI solutions to enhance overall verification efficiency while guaranteeing verification performance.

The booming of learning-based Artificial Intelligence (AI) enables the integration of Big Data and emerging computing architectures, which facilitate the Edge-AI-as-a-Service (EAaaS) in the edge-cloud continuum. To meet the emerging demands, such as privacy preservation and autonomy, blockchain-enabled federated learning (B-FL) is proposed, which further provides decentralized processing, data falsification avoidance, and learning model reliability. However, synchronous global aggregation, which is deployed in most existing B-FL paradigms, is dragging down the performances due to the data and computing resources heterogeneity of diverse edge devices. In addition, the restricted resources of edge devices pose further challenges in executing learning tasks and blockchain-based consensus simultaneously. To solve these issues, we propose a blockchained dual-asynchronous federated learning (BAFL-DT) service model for EAaaS in the digital twin empowered edge-cloud continuum. In BAFL-DT, federated learning services are run on local edge devices, while the global aggregation is achieved by the consensus process of digital twins implemented in the cloud. Besides, dual-asynchronous FL allows both local training and global aggregation to be performed in an asynchronous manner, which is uniquely enabled by the proposed paradigm. Extensive evaluations of real-world datasets testify to the superior performances of EAaaS by improving accuracy and efficiency.

The surge in data collected by local devices has given rise to a distributed machine learning architecture namedFederatedLearning (FL) for privacy-preserving model training. However, the security of centralized aggregation of local models becomes a primary concern, which can be mitigated byBlockchain-enabledFederatedLearning (BFL) to facilitate decentralized model aggregation. In BFL, consensus and incentive are two of the key components that impact the scalability, security, and consistency of the system. Existing joint solutions focus on selecting a block producer based on client contributions to model training but overlook contributions to blockchain consensus and lack consideration for correlations across communication rounds, inevitably affecting incentive performance. Motivated by these, we make the first attempt to achieve blockchain consensus with along-term incentive guaranteefor BFL systems. Following a generalizable BFL workflow, we decouple the global contribution of BFL clients into four rigorously modeled metrics, and formulate the block producer selection problem as a long-term total contribution maximization problem with reward constraints. ALong-termProof-of-Contribution algorithm named LPoC is developed to handle this problem efficiently. In each communication round, LPoC identifies an optimal block producer that can maximize total contributions from a long-term perspective while allocating rewards to continuously motivate clients to contribute to BFL. We provide a detailed analysis of time complexity and performance bounds, followed by extensive experimental evaluations. The results demonstrate the effectiveness of LPoC in maximizing long-term total contribution, improving consensus efficiency, and upgrading training performance.

MobileEdgeComputing (MEC) is an emerging technology, where App vendors are allowed to cache multiple data replicas on geographically distributed edge servers to serve adjacent mobile subscribers. However, this benefit introduces an extra workload for edge servers and App vendors, as they must audit the integrity of multiple data replicas periodically considering various threats caused by distributed and dynamic MEC environments. The large-scale growth of data replicas certainly is a challenge to design more efficientEdgeDataIntegrity (EDI) verification approaches. Existing solutions are mostly limited to improving efficiency by optimizing proof generation and verification methods, while the improvement is still far from satisfactory due to adopting indiscriminate inspection philosophy (checking all data replicas without discrimination). In this paper, we make the first attempt to abstract a pre-processing phase and correspondingly study theUnreliable dataReplicaSelection (URS) problem. It can be seamlessly integrated into existing EDI solutions by solving the URS problem at the start of each verification round. Such pre-selection can significantly enhance overall EDI verification efficiency by incorporating the cache serviceQualityofService (QoS) and verification success rate, especially in scenarios with a large number of data replicas. Specifically, we first formalize the URS problem as a constrained optimization problem, and further prove its$\mathcal {NP}$-hardness. To address the problem efficiently, we transform it into an easy-to-handle form and develop aPriority-based approach named URS-P. Both theoretical analysis and experimental evaluation validate the effectiveness and efficiency of our proposed solution.

Internet of Things (IoT) is experiencing fast proliferation with emerging trends in autonomy and local decision-making to avoid the explosive burden on network infrastructure between cloud and edge. Thereby, blockchain as a Service (BaaS) for IoT, as an emerging distributed services computing paradigm, has drawn intense attention due to its decentralization, auditability, and tamper-resistance. However, the primary challenge is to design a tailor-made consensus protocol that is applicable to BaaS for IoT. Existing consensus protocols generally focus on power-intensive environments, which is not feasible for power-constrained BaaS-enabled IoT systems. In this article, to fully exploit BaaS's superiority (e.g., to sharing data securely), we propose a lightweight model-based evolutionary consensus protocol called Proof of Evolutionary Model (PoEM) that can improve the quality of BaaS in IoT environments. Beyond existing rule-based consensus protocols, PoEM iteratively trains a machine learning model to achieve consensus. In this way, PoEM enhances consensus efficiency and enables low-performance IoT devices to be involved. Moreover, considering IoT environments’ dynamics, a novel mechanism is designed to manage nodes joining and exiting dynamically. Extensive analytical and experimental results show PoEM's improved consensus efficiency and applicability in dynamic BaaS-based IoT environments while providing high-level security guarantees.

Federated learning (FL) is a machine learning framework for collaborative data mining in many scenarios (e.g. Internet of Things) due to its privacy-preserving feature. However, various attacks arise security concerns of FL, such as poisoning, backdoor, and DDoS attacks. Several blockchain-based FL schemes strengthen credibility and security without considering the increased communication overhead. Some existing work compresses local updated gradients to sign vectors to lower communication overhead at the expense of model accuracy. To address the above concerns, this paper offers a blockchain-based asynchronous SignSGD (BASS) scheme. A novel asynchronous sign aggregation algorithm is introduced to ensure model accuracy even if the local updated gradients are compressed to sign vectors. Considering the unstable network connection on IoT, a consensus algorithm that elects multiple leader nodes enables reliable global model aggregation. The introduced blockchain improves credibility and security without downgrading efficiency. Empirical studies show that BASS outperforms other schemes in efficiency, model accuracy, and security.

With the growing proliferation of intelligent end devices and data analytics techniques, real momentum towards the development of smart healthcare networks (SHN) has already been evident. Multiple parties in SHNs continuously exchange medical data in order to achieve a precise diagnosis and process optimization. Privacy issue emerges since medical data are susceptible, while the combination of a series of medical data may lead to further privacy leakage. Adversaries launch unceasingly launch poisoning attacks, a dominant attack to maliciously manipulate data, severely impact the authenticity of the data transmitting over the SHNs, leading to misdiagnosing or even physical damage. In this paper, we propose a personalized differential privacy model built upon blockchain, in which the community density is exploited to customize the degree of privacy protection and inject corresponding noise data. Besides using blockchain as the underlying network architecture to defeat poisoning attacks. The proposed model can guarantee the authentication of the differentially private data, traceability of data, and single-point failure avoidance in SHN. Evaluation and extensive results using real-world data sets demonstrate the superiority of the proposed model.

Wireless-powered mobile-edge computing (MEC) emerges as a crucial component in the Internet of Things (IoTs). It can cope with the fundamental performance limitations of low-power networks, such as wireless sensor networks or mobile networks. Although computation offloading and resource allocation in MEC have been studied with different optimization objectives, performance optimization in larger-scale systems still needs to be further improved. More importantly, energy efficiency is also a key issue as well as computation offloading and resource allocation for wireless-powered MEC. In this article, we investigate the joint optimization of computation rate and energy consumption under limited resources, and propose an online offloading model to search for the asymptotically optimal offloading and resource allocation strategy. First, the joint optimization problem is modeled as a mixed integer programming (MIP) problem. Second, a deep reinforcement learning (DRL)-based method, energy efficiency computation offloading using probabilistic action generating (ECOPG), is designed to generate the joint optimization policy for computation offloading and resource allocation. Finally, to avoid the curse of dimensionality in large network scales, an action exploration mechanism based on probability is introduced to accelerate the convergence rate by targeted sampling and dynamic experience replay. The experimental results demonstrate that the proposed methods significantly outperform other DRL-based methods in energy consumption, and gain better computation rate and execution efficiency at the same time. With the expansion of the network scale, the improvements become more apparent.

With the fast boom of Internet of Medical Things (IoMT) devices and an increasing focus on personal health, personal health data are extensively collected by IoMT and stored as personal health records (PHRs). PHRs are frequently shared for accurate diagnosis, prognosis prediction, health advice consulting, etc. Since PHRs are highly private, the data-sharing process leads to wide-ranging concerns on privacy leakage and security compromise. Existing research has shown that the centralized systems, as the mainstream mode, are under the great risks. Motivated by this, we propose a consortium blockchain-based PHR management and sharing scheme, which is both security aware and privacy preserving. We adopt the interplanetary file system (IPFS) to store the PHR ciphertext of IoMT. Then, zero-knowledge proof can provide evidence for verifying keyword index authentication on blockchain. Moreover, the scheme jointly leverages modified attribute-based cryptographic primitives and tailor-made smart contracts to achieve secure search, privacy preservation, and personalized access control in IoMT scenarios. Security analysis is conducted to show that the designed protocols attain the expected design goals. This is followed by extensive evaluation results derived from real-world data sets, which demonstrate the superiority of the proposed scheme over current leading ones.

Diverse technologies, such as machine learning and big data, have been driving the prosperity of the Internet of Things (IoT) and the ubiquitous proliferation of IoT devices. Consequently, it is natural that IoT becomes the driving force to meet the increasing demand for frictionless transactions. To secure transactions in IoT, blockchain is widely deployed since it can remove the necessity of a trusted central authority. However, the mainstream blockchain-based IoT payment platforms, dominated by Proof-of-Work (PoW) and Proof-of-Stake (PoS) consensus algorithms, face several major security and scalability challenges that result in system failures and financial loss. Among the three leading attacks in this scenario, double-spend attacks and long-range attacks threaten the tokens of blockchain users, while eclipse attacks target Denial of Service. To defeat these attacks, a novel bidirectional-linked blockchain (BLB) using chameleon hash functions is proposed, where bidirectional pointers are constructed between blocks. Furthermore, a new committee members auction (CMA) consensus algorithm is designed to improve the security and attack resistance of BLB while guaranteeing high scalability. In CMA, distributed blockchain nodes elect committee members through a verifiable random function. The smart contract uses Shamir’s secret-sharing scheme to distribute the trapdoor keys to committee members. To better investigate BLB’s resistance against double-spend attacks, an improved Nakamoto’s attack analysis is presented. In addition, a modified entropy metric is devised to measure eclipse attack resistance across different consensus algorithms. Extensive evaluation results show the superior resistance against attacks and demonstrate high scalability of BLB compared with current leading paradigms based on PoS and PoW.

To accommodate heterogeneous and sophisticated network services, Network Function Virtualization (NFV) is invented as a hopeful networking technology. The most distinct feature of NFV is that it separates network functions from physical hardware. In the NFV architecture, various types of Virtual Network Functions (VNFs) are placed on specific software-based middleboxes by telecom providers. Traffic traverses through a sequence of Virtual Network Functions (VNFs) in pre-defined order, which is named as Service Function Chain (SFC). However, how to effectively place VNFs at different locations and steer SFC requests while minimizing energy consumption is still an open problem. Accordingly, we investigate on the joint optimization of VNF placement and traffic steering for energy efficiency in telecom networks. We first present the power consumption model in NFV-enabled telecom networks, and then formulate the studied problem as an Integer Linear Programming (ILP) model. Since the problem is proved as NP-hard, we design a polynomial algorithm that can achieve near-optimal performances based on the Markov approximation technique. In addition, our algorithm can be extended to an online version to serve dynamic arriving SFC requests. The online algorithm achieves a near-optimal long-term averaged performance. Extensive simulation results show that compared with the benchmark algorithms, in the offline and online scenario, our algorithm can reduce up to 14.08 and 13.72 percent power consumption in telecom networks, respectively.

A Covert Electricity-Theft Cyberattack Against Machine Learning-Based Detection Models

Internet of Things (IoT) anomaly detection is significant due to its fundamental roles of securing modern critical infrastructures, such as falsified data injection detection and transmission line faults diagnostic in smart grids. Researchers have proposed various detection methods fostered by machine learning (ML) techniques. Federated learning (FL), as a promising distributed ML paradigm, has been employed recently to improve detection performance due to its advantages of privacy-preserving and lower latency. However, existing FL-based methods still suffer from efficiency, robustness, and security challenges. To address these problems, in this article, we initially introduce a blockchain-empowered decentralized and asynchronous FL framework for anomaly detection in IoT systems, which ensures data integrity and prevents single-point failure while improving the efficiency. Further, we design an improved differentially private FL based on generative adversarial nets, aiming to optimize data utility throughout the training process. To the best of our knowledge, it is the first system to employ a decentralized FL approach with privacy-preserving for IoT anomaly detection. Simulation results on the real-world dataset demonstrate the superior performance from aspects of robustness, accuracy, and fast convergence while maintaining high level of privacy and security protection.

Artificial intelligence (AI) requires a large amount of data to train high-quality machine learning (ML) models. However, due to privacy issues, individuals or organizations are not willing to share data with others, which results in “data islands”. This motivates the emergence of Federated Learning (FL), a novel ML framework allowing clients to exchange model parameters rather than the raw data. Unfortunately, the private data may be reconstructed by malicious participants by exploiting the context of model parameters in FL. This poses further challenges to privacy protection. To address this issue, we propose to integrate Wasserstein Generative Adversarial Network (WGAN) and differential privacy (DP) to protect the model parameters. WGAN is used to generate controllable random noise, which is then injected into model parameters. The new mechanism satisfies DP requirements while the data utility is highly improved. We experimentally demonstrate superior performances from aspects of convergence, accuracy, and data utility.

With the widespread of 5G networks, the application of Federated Learning (FL) in Internet of Things (IoT) has become a trend. However, the trust problem caused by the centralized aggregation server, and the inefficiency problem caused by the low-performance devices, are still key challenges. Several studies involving asynchronous FL have been conducted to accelerate the training process, but they usually have a decreased model performance. In this paper, a blockchain-based asynchronous federated learning framework with a dynamic scaling factor is proposed. By adopting the blockchain, the trust problem among devices can be addressed. Meanwhile, the novel dynamic scaling factor is proposed to help improve the FL efficiency and accuracy. Extensive experiments are conducted on heterogeneous devices and the results show that the proposed framework mitigates the impact of low-performance devices while being as efficient as traditional FL with the extra benefit of alleviating the trust problem among IoT devices.

In the Internet of Vehicles (IoVs), cooperative perception allows vehicles to share the sensor data with each other, so as to increase the perception range of vehicles beyond their field of view. This enables vehicles to obtain more accurate sensing information while driving and improves the safety of vehicles on the road. However, malicious nodes can send false information and poison the cooperative perception process. Therefore, how to guarantee the security of cooperative perception is crucial. In this paper, we propose a blockchain-based scheme for the post hoc electronic forensics of cooperative perception. Applying blockchain in cooperative perception is however challenging. Due to the high mobility of vehicles, the connection of vehicles to the Internet is intermittent and unpredictable. In this scenario, the security and effectiveness of blockchain can not be guaranteed as vehicles are offline.11Offline refers to that the vehicles can not connect to the Internet, but they can use vehicle-to-vehicle communication to share data. and can not update the blockchain on time. On addressing the issue, We develop an offline blockchain scheme that is composed of offline and online phases. In the offline phase, vehicles transact by sending a commitment. In the online phases before and after the offline phase, the deposit and arbitration mechanisms are proposed to defeat potential attacks in the offline phase. Lastly, the consortium blockchain is deployed to store the records of the cooperative perception process so that the records are tamper-proof and can be traced. Using extensive evaluations, we show the effectiveness of the proposed scheme.

With the evolving Internet of Vehicles (IoVs), the onboard resources of vehicles in computing and communication are experiencing fast growth. The sharing of road information and computing results among vehicles in proximity can effectively improve the utility of IoVs. However, remote inter-vehicular resource sharing, e.g., information and computing resource sharing, remains an under-explored issue. Motivated by this, we propose a novel digital twin based fair trading platform built upon consortium blockchain to enable city-wide vehicular resource sharing. Specifically, we first develop a digital twin based vehicular platform to enable vehicular resource sharing in the cloud. To track and secure the resource sharing among digital twins, the consortium blockchain is deployed, which is enforced by the designed smart contracts with an efficient Proof-of-Stake (PoS) consensus algorithm. In addition, an innovative incentive mechanism is devised to motivate the city-wide resource sharing for vehicles, which can maximize the profits of task publishers. Using extensive evaluations, we show the effectiveness of the proposed system.

Cognitive computing, a revolutionary AI concept emulating human brain's reasoning process, is progressively flourishing in the Industry 4.0 automation. With the advancement of various AI and machine learning technologies the evolution toward improved decision making as well as data-driven intelligent manufacturing has already been evident. However, several emerging issues, including the poisoning attacks, performance, and inadequate data resources, etc., have to be resolved. Recent research works studied the problem lightly, which often leads to unreliable performance, inefficiency, and privacy leakage. In this article, we developed a decentralized paradigm for big data-driven cognitive computing (D2C), using federated learning and blockchain jointly. Federated learning can solve the problem of “data island” with privacy protection and efficient processing while blockchain provides incentive mechanism, fully decentralized fashion, and robust against poisoning attacks. Using blockchain-enabled federated learning help quick convergence with advanced verifications and member selections. Extensive evaluation and assessment findings demonstrate D2C's effectiveness relative to existing leading designs and models.

Driverless parking, an influential application of Mobility as a Service (MaaS) model, is one of the clear early benefits for autonomous vehicles, given often narrow spaces and multiple potential hazards (such as pedestrians stepping out from in between other vehicles). In recent years, real momentum has been building up for designing automated parking models for vehicles. However, in such an autonomous parking design, location privacy and identity privacy issues are always overlapping due to the improper sharing of data. Most existing studies barely investigate and poorly address such privacy issues. Motivated by this, we develop (and evaluate) an experience-driven, secure and privacy-aware framework of parking reservations for automated cars. Our idea of using differential privacy with zero-knowledge proof provides both security and privacy guarantees to users. Furthermore, the performance of the developed model is enhanced by exploiting reinforcement learning approach such that the utility of the system and the parking reservation rate can be maximized. Extensive evaluation demonstrates the superiority of the proposed model.

Fog computing is an emergent computing paradigm that extends the cloud paradigm to the edge. With the explosive growth of smart devices and massive data generated everyday, cloud computing no longer matches the requirements of the Internet of Things (IoT) era, such as low latency, uninterrupted service and location awareness. Thus, fog computing has been introduced as a complement of the current cloud computing model to meet the requirements in IoT. Fog computing is a relatively new networking paradigm and considered as a promising solution to support IoT scenarios. On the one hand, fog computing inherits many features from cloud; on the other hand, fog computing also inherits some challenges and issues from cloud computing: privacy issue is one of them. In this paper, we propose a personalized differential privacy model based on the distance between two fog nodes in a fog network. We also identify the collusion attack in differential privacy framework which compromised the personalized Laplace function. Based on that, we develop a personalized differential privacy model, which not only eliminate this particular attack but also optimize the trade-off between privacy preserving and data utility.

With the ensuing surge in data communication volume and the growing need for privacy protection, limiting centralized data collection to the minimum required for specific tasks has been mandatory in industries. This is now guided by the modern privacy legislation, namely, the General Data Protection Regulation and the California Consumer Protection Act. Privacy leakage has become increasingly serious because of massive volume and a variety of data transmission and Quality-of-Service (QoS) requirements in the Industrial Internet-of-Things (IIoT) networks. Although differential privacy is the core privacy protection paradigm, most of its extensions assume all parties share the same level of privacy requirements, which cannot meet varying needs and QoS of IIoT devices in practice. In addition, with multiple paths access to the cloud server (often operated by the trusted third party in IIoT) for higher reliability and performance, satisfying both the privacy and QoS is nontrivial during the data transmission. The usual transmission over both the cellular and WiFi interfaces simultaneously for continuous connectivity among devices, edge networks, and the server is crucial. As a result, we observe that IIoT data privacy is highly vulnerable to collusion attacks. Motivated by this observation, we develop a detailed QoS modeling for multipath TCP over IIoT and propose a QoS-aware personalized privacy protection model. Our model works in two different layers: one at the cloud server and another at the network edges (access points/base station). The aim is not only to balance the load but also to achieve the required QoS and optimize the tradeoff between privacy protection and efficiency. The extensive experimental results based on the real-world data sets illustrate the superiority of the proposed model in terms of privacy protection and efficiency.

As the extension of cloud computing and a foundation of IoT, fog computing is experiencing fast prosperity because of its potential to mitigate some troublesome issues, such as network congestion, latency, and local autonomy. However, privacy issues and the subsequent inefficiency are dragging down the performances of fog computing. The majority of existing works hardly consider a reasonable balance between them while suffering from poisoning attacks. To address the aforementioned issues, we propose a novel blockchain-enabled federated learning (FL-Block) scheme to close the gap. FL-Block allows local learning updates of end devices exchanges with a blockchain-based global learning model, which is verified by miners. Built upon this, FL-Block enables the autonomous machine learning without any centralized authority to maintain the global model and coordinates by using a Proof-of-Work consensus mechanism of the blockchain. Furthermore, we analyze the latency performance of FL-Block and further derive the optimal block generation rate by taking communication, consensus delays, and computation cost into consideration. Extensive evaluation results show the superior performances of FL-Block from the aspects of privacy protection, efficiency, and resistance to the poisoning attack.

Fog computing faces various security and privacy threats. Internet of Things (IoTs) devices have limited computing, storage, and other resources. They are vulnerable to attack by adversaries. Although the existing privacy-preserving solutions in fog computing can be migrated to address some privacy issues, specific privacy challenges still exist because of the unique features of fog computing, such as the decentralized and hierarchical infrastructure, mobility, location and content-aware applications. Unfortunately, privacy-preserving issues and resources in fog computing have not been systematically identified, especially the privacy preservation in multiple fog node communication with end users. In this paper, we propose a dynamic MDP-based privacy-preserving model in zero-sum game to identify the efficiency of the privacy loss and payoff changes to preserve sensitive content in a fog computing environment. First, we develop a new dynamic model with MDP-based comprehensive algorithms. Then, extensive experimental results identify the significance of the proposed model compared with others in more effectively and feasibly solving the discussed issues.

Increasing massive volume of data are generated every single second in this big data era. With big data from multiple sources, adversaries continuously mine private information for potential benefits. Motivated by this, we propose a generative adversarial net (GAN) driven noise generation method under the framework of differential privacy. We add one more perceptron, which is a specifically devised differential privacy identifier. After the generator produces the noise, the discriminator and the proposed identifier game with each other to derive the Nash Equilibrium. Extensive experimental results demonstrate the proposed model meets differential privacy constraints and upgrade data utility simultaneously.

Fast proliferation of mobile devices significantly promotes the development of mobile social networks. Users tend to interact with friends via multiple social networks. Multiple social networks identification is of great significance in terms of both attack and defense. Current methods either focus on the profile matching or network structure to re-identify a specific user. However, the accuracy are not satisfying with relative high error rate. In this paper, we propose a new Friendship learning-Based Identification (FBI) method to discriminate multiple pseudo identities of a real-world individual. We aim at providing potential attack mechanism to following privacy protection research. Firstly, we develop a new identification method based on friendship matching. Then, we implement a weighted mechanism which takes profile, network structure, and friendship into consideration. Furthermore, machine learning is leverage to further optimize the parameters and improve the accuracy. In addition, extensive experimental results show the superior of the FBI comparing to existing ones.

In the age of big data, the rapid development of social networking applications has become an improtant data source, while the massive collection of personal data leads to significant privacy concerns. Differential privacy emerged as an effective tool to get access to useful information while provide strong privacy guarantees. However, most the current proposed solutions suppose that all individuals across the network require a uniform level of privacy protection, which rules out of individuals' personalized requirements. Aiming at solving this problem, in this paper, we propose a trust-grained personalized differential privacy mechanism, called TGDP, by combining the notion of trust. Specifically, whenever a user wants to get another user's personal information, the proposed mechanism returns a corresponding private response in which the privacy level selected for each individual depend on the trust value between them in the network. Compared with traditional methods, the scheme can provide a fine-grained differential privacy protection method, while guarantee the utility of social networks. Finally, the scheme is evaluated analytically, and demonstrated experimentally on the real- world data, which reflects its effectiveness and utility.

Due to dramatically increasing information published in social networks, privacy issues have given rise to public concerns. Although the presence of differential privacy provides privacy protection with theoretical foundations, the trade-off between privacy and data utility still demands further improvement. However, most existing works do not consider the impact of the adversary in the measurement of data utility. In this paper, we firstly propose a personalized differential privacy based on social distance. Then, we analyze the maximum data utility when users and adversaries are blind to the strategy sets of each other. We formulize all the payoff functions in the differential privacy sense, which is followed by the establishment of a Static Bayesian Game. The trade-off is calculated by deriving the Bayesian Nash Equilibrium. In addition, the in-place trade-off can maximize the user' data utility if the action sets of the user and the adversary are public while the strategy sets are unrevealed. Our extensive experiments on the real-world dataset prove the proposed model is effective and feasible.

The rapid proliferation of smart mobile devices has significantly enhanced the popularization of the cyber-physical social network, where users actively publish data with sensitive information. Adversaries can easily obtain these data and launch continuous attacks to breach privacy. However, existing works only focus on either location privacy or identity privacy with a static adversary. This results in privacy leakage and possible further damage. Motivated by this, we propose a hybrid privacy-preserving scheme, which considers both location and identity privacy against a dynamic adversary. We study the privacy protection problem as the tradeoff between the users aiming at maximizing data utility with high-level privacy protection while adversaries possessing the opposite goal. We first establish a game-based Markov decision process model, in which the user and the adversary are regarded as two players in a dynamic multistage zero-sum game. To acquire the best strategy for users, we employ a modified state-action-reward-state-action reinforcement learning algorithm. Iteration times decrease because of cardinality reduction from n to 2, which accelerates the convergence process. Our extensive experiments on real-world data sets demonstrate the efficiency and feasibility of the propose method.

There is a growing trend towards attacks on database privacy due to great value of privacy information stored in big data set. Public's privacy are under threats as adversaries are continuously cracking their popular targets such as bank accounts. We find a fact that existing models such as K-anonymity, group records based on quasi-identifiers, which harms the data utility a lot. Motivated by this, we propose a sensitive attribute-based privacy model. Our model is the early work of grouping records based on sensitive attributes instead of quasi-identifiers which is popular in existing models. Random shuffle is used to maximize information entropy inside a group while the marginal distribution maintains the same before and after shuffling, therefore, our method maintains a better data utility than existing models. We have conducted extensive experiments which confirm that our model can achieve a satisfying privacy level without sacrificing data utility while guarantee a higher efficiency.