Federated learning is a machine learning paradigm through training on locally private data and aggregating local models to generate a federated model. However, due to the heterogeneity problems (data heterogeneity and model heterogeneity), federated learning suffers from convergence difficulties and excessive aggregation overhead on decentralized participants. Additionally, federated learning faces privacy concerns during the aggregation of local models. To this end, in this work, we propose FEDINF, an efficient and secure inference with federated participants. Specifically, FEDINF features the following characteristics. FEDINF overcomes convergence challenges through federated inference instead of federated training, which reduces computation and communication overhead. Moreover, we design secure computation protocols and aggregation mechanisms to measure contributions, and handle both data and model heterogeneity without sacrificing privacy. Results of experimental evaluations on common datasets demonstrate that the proposed FEDINF outperforms the existing federated learning approaches in terms of efficiency and heterogeneity.

An attacker can determine if a specific input belongs to a deep learning model's training set by analyzing the complete confidence vector output, known as a membership inference attack. To counter this type of attack, a common defense strategy is to add adversarial noise to the confidence vector to enhance the model's resilience. However, existing research indicates that defenses against adversarial examples may introduce new security risks to membership inference defenses via adversarial examples. Against this backdrop, this paper proposes a more robust adversarial example defense strategy. By generating adversarial examples with distributions similar to normal samples, we can reduce the impact of distributional differences on the defense model's security. Leveraging normalizing flow, adding noise to the hidden layer of a flow model trained on normal samples generates adversarial examples that resemble normal ones, enhancing defense robustness. Additionally, limiting the information accessible to the attack model further strengthens robustness. To accelerate convergence, a bidirectional mean update method is employed. The proposed strategy demonstrates effectiveness not only in defending against membership inference attacks but also in mitigating attribute inference attacks. Finally, experiments on real-world datasets validate the effectiveness of the proposed strategy.

A hierarchical labeling system for mobile applications (apps) benefits a wide range of downstream businesses that integrate the labeling with their proprietary user data, to improve user modeling. Such a label hierarchy can define more granular labels that capture detailed app features beyond the limitations of traditional broad app categories. In this paper, we address the problem of hierarchical multilabel classification for apps by using their textual information such as names and descriptions. We present: 1) HMCN (Hierarchical Multilabel Classification Network) for handling the classification from two perspectives: the first focuses on a multilabel classification without hierarchical constraints, while the second predicts labels sequentially at each hierarchical level considering such constraints; 2) HMCL (Hierarchical Multilabel Contrastive Learning), a scheme that is capable of learning more distinguishable app representations to enhance the performance of HMCN. Empirical results on our Tencent App Store dataset and two public datasets demonstrate that our approach performs well compared with state-of-the-art methods. The approach has been deployed at Tencent and the multilabel classification outputs for apps have helped a downstream task--credit risk management of users--improve its performance by 10.70% with regard to the Kolmogorov-Smirnov metric, for over one year.

Mobile edge caching (MEC) has grown substantially with the rapid development in scale and complexity of data traffic. By exploiting the expansive coverage of autonomous aerial vehicles (AAVs), MEC enables services for massive vehicle users (VUs) simultaneously, which is promising for enhancing network transmission efficiency. Nonetheless, due to challenges arising from the timeliness and freshness of content services caused by AAVs’ limited endurance and airborne capacity, caching strategy considering the real-time of content in large-scale dynamic Internet of Vehicles (IoV) environments remains open. With the above consideration, in this article, the cache refreshing cycle and content placement are jointly optimized in the cache-enabled AAV-assisted vehicular integrated networks (CAVINs) to minimize the content Age of Information (AoI) and energy consumption of the macro AAV. Since the joint optimization problem is variational coupled with nonconvex binary constraints, it is decoupled and solved by a double-iteration method. Specifically, the optimal cache refreshing cycle is derived in semi-closed form with the Karush-Kuhn-Tucker (KKT) conditions. The locally optimal solution of the content placement is obtained through successive convex approximation (SCA). Simulation results corroborate the effectiveness and superiority of the proposed scheme.

Decentralized Knowledge Graph (DKG) platforms allow the sharing of knowledge with multiple owners. While data owners can share their data with others by encrypting their data before sharing it, this naïve approach prevents data encrypted by different owners from being queried together, as it compromises query verifiability, an essential DKG platform feature. We propose Pistis, the first DKG platform capable of preserving ownership while also enabling verifiable SPARQL queries. Two novel techniques facilitate this: owner-managed end-to-end encryption and collaborative query verification. In Pistis, data owners thus encrypt their data individually and collaborate to construct an authenticated data structure (ADS) with a global key by means of secret sharing and secure multi-party computation. Then, by indexing KG data as ciphertext over the ADS, Pistis offers a cryptographic scheme called VO-SPARQL that facilitates verifiable queries on encrypted KG data with multiple owners. Pistis provides succinct proofs for two-stage SPARQL queries, including subgraph queries based on the ADS and aggregation on encrypted intermediate results based on a key-aggregate cryptographic primitive. A theoretical analysis and an empirical study provide detailed insight into the performance of Pistis while offering provable security.

Decentralized identity (DID) is rapidly emerging as a promising alternative to centralized identity infrastructure, offering numerous real-world applications. However, existing DID systems are confronted with trust concerns, as any distributed node can act as a credential issuer and be considered trusted, which is impractical. Effective trust management (TM) protocols are critical for system trustworthiness but face two primary challenges: preserving user feedback privacy to meet regulation requirements and building resilience against trust attacks to prevent manipulation. While privacy-preserving TM protocols effectively safeguard sensitive data, they often obscure feedback, hindering anomaly detection and complicating efforts to counter trust attacks. To address these issues, we propose DidTrust, a novel decentralized identity trust management protocol that bridges data privacy and resilience to trust attacks. DidTrust features a feedback data privacy preservation protocol that conceals feedback data while maintaining authorizability and verifiability. It also implements countermeasures against cooperative and individual trust attacks, improving detection accuracy without compromising privacy. To improve efficiency, we introduce a feedback compression module for large-scale sparse matrices. Rigorous analysis proves DidTrust to be universally composable (UC) secure under a malicious model, and experiments demonstrate its improved computational and storage efficiency while achieving higher trust attack detection rates compared to BC-Trust.

Decentralized identity (DID) is a transformative paradigm that leverages blockchain, decentralized identifiers and verifiable credentials (VCs) to enable self-sovereign and decentralized identity management with myriad application areas. However, existing DID implementations are confronted with two key challenges: insufficient decentralization and vulnerability to mobile adversary attacks. First, they paradoxically introduce central identity resolvers, intermediaries or static committees to manage critical identity services, key management or credential issuance, which violates the decentralized controlling aim against a single point of failure. Second, these systems are vulnerable to mobile adversaries who can gradually compromise multiple nodes or committee members over a long period, eventually seizing control of the system. In this paper, we propose DP-DID, the first dynamic and proactive decentralized identity system specifically designed to resist mobile adversary attacks in dynamic committee settings. To eliminate centralized authorities, DP-DID leverages blockchain, dynamic committees and BLS1signatures, which achieves decentralization. In addition, we design a dynamic and batch proactive secret sharing (DBPSS) scheme for DP-DID to ensure proactive security against mobile adversary attacks. This is achieved by allowing at mostt(threshold) committees to be corrupted per period, with the set of corrupted committees changing dynamically even if all players are eventually compromised. By incorporating DBPSS, DP-DID achieves efficient key management for multiple users in dynamic settings, enhancing overall system scalability. Through rigorous analysis, DP-DID is proven to be forward secure and secure against mobile adversary attacks under a widely adopted malicious model. Extensive experiments show that DP-DID has efficient performance, and our DBPSS scheme outperforms FaB-DPSS by over 11.67× in key handover efficiency.

The critical importance of monitoring and recognizing human emotional states in healthcare has led to a surge in proposals for EEG-based multimodal emotion recognition in recent years. However, practical challenges arise in acquiring EEG signals in daily healthcare settings due to stringent data acquisition conditions, resulting in the issue of incomplete modalities. Existing studies have turned to knowledge distillation as a means to mitigate this problem by transferring knowledge from multimodal networks to unimodal ones. However, these methods are constrained by the use of a single teacher model to transfer integrated feature extraction knowledge, particularly concerning spatial and temporal features in EEG data. To address this limitation, we propose a multi-teacher knowledge distillation framework enhanced with a Large Language Model (LLM), aimed at facilitating effective feature learning in the student network by transferring knowledge of extracting integrated features. Specifically, we employ an LLM as the teacher for extracting temporal features and a graph convolutional neural network for extracting spatial features. To further enhance knowledge distillation, we introduce causal masking and a confidence indicator into the LLM to facilitate the transfer of the most discriminative features. Extensive testing on the DEAP and MAHNOB-HCI datasets demonstrates that our model outperforms existing methods in the modality-incomplete scenario. This study underscores the potential application of large models in this field.

Rate-splitting multiple access (RSMA), space division multiple access (SDMA), and non-orthogonal multiple access (NOMA) have gained significant popularity and are extensively utilized across various domains. However, it is still unclear whether hybridRSMA-SDMA-NOMA (HybridRDN) would seamlessly combine the advantages of RSMA, SDMA, and NOMA to contribute to the computation offloading of autonomous vehicle systems. To address the above issue, this paper introduces a novel HybridRDN-assisted computation offloading fleet (COF) scheme tailored for autonomous vehicle systems. First, we propose a stochastic-geometry-aided method to model the offloading framework. Afterwards, the task vehicles (TVs) ingeniously employ the proposed HybridRDN scheme to offload tasks to the resource vehicles (RVs) in each COF to relieve their computational burden. Diverging from the sole optimization of the task segmentation ratio or the transmission rate, a joint optimization problem involving the transmission weighting factor, the HybridRDN precoding matrix, the common rate, and the task segmentation ratio, is formulated, which aims to minimize the average delay of the COF system while approaching the rate performance of the ideal HybridRDN. Furthermore, a delay-optimal alternating optimization algorithm (DOAOA) is developed to obtain the solution for the optimization problem. Experimental results validate the plausibility and superiority of the proposed framework compared to the state-of-the-art schemes.

Facial expression recognition is a technology that involves analyzing and interpreting human facial expressions to determine individual expressions or states. Mobile crowdsensing (MCS), a promising sensing paradigm, makes it easy to capture facial images and benefits facial expression recognition. Existing inference models for facial expression recognition usually rely on facial feature vectors or facial images, increasing privacy concerns about expression. For this reason, this paper proposes a privacy-preserving facial expression recognition scheme through MCS, named RAPOO, which falls in a client-server architecture. Roughly speaking, a user captures facial images using mobile devices and requests a recognition service provided by a cloud computing center. To protect the privacy of expressions, our approach focuses on designing secure computation protocols required by facial expression recognition necessarily, such as secure vector distance calculation and secure top-$k$query. These protocols enable facial expression recognition over encrypted data directly. To speed up the recognition and store encrypted feature vectors, a$k$-D tree data structure is introduced. The security analysis confirms that RAPOO effectively preserves the confidentiality of personal expressions. Extensive experimental evaluations show that our solution obtains a three-order-of-magnitude speedup in terms of computational overhead compared with the state-of-the-art.

Abstract The threat of Scan and Foothold Attack to the Network Edge (SFANE) is increasing, which greatly affects the application and development of edge computing network architecture. However, existing works focus on the implementation of specific technologies that resist the SFANE but ignore the effectiveness analysis of them. To overcome this limitation, this paper constructs probabilistic models for evaluating network edge's resistance against SFANE. In particular, the attacker models of the SFANE based on the ATT&CK model are first formalized. Afterward, according to the state‐of‐the‐art defense technologies, three different defense strategies are illustrated: no defense, address mutation, and fingerprint decoy. Subsequently, three different probabilistic models are constructed to provide a deeper analysis of the theoretical effect of these strategies on resisting the SFANE. Finally, the experimental results show that the actual defense effect of each strategy almost perfectly follows its probabilistic model.

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

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

Internet of Things (IoT) applications have penetrated into all aspects of human life. Millions of IoT users and devices, online services, and applications combine to create a complex and heterogeneous network, which complicates the digital identity management. Distributed identity is a promising paradigm to solve IoT identity problems and allows users to have soverignty over their private data. However, the existing state-of-the-art methods are unsuitable for IoT due to continuing issues regarding resource limitations for IoT devices, security and privacy issues, and lack of a systematic proof system. Accordingly, in this article, we propose SmartDID, a novel blockchain-based distributed identity aimed at establishing a self-sovereign identity and providing strong privacy preservation. First, we configure IoT devices as light nodes and design a Sybil-resistant, unlinkable, and supervisable distributed identity that does not rely on central identity providers. We further develop a dual-credential model based on commitment and zero-knowledge proofs to protect the privacy of sensitive attributes, on-chain identity data, and linkage of credentials. Moreover, we combine the basic credential proofs to prove the knowledge of solutions to more complex problems and create a systematic proof system. We go on to provide the security analysis of SmartDID. Experimental analysis shows that our scheme achieves better performance in terms of both credential generation and proof generation when compared with CanDID.

The ability to decentralize knowledge graphs (KG) is important to exploit the full potential of the Semantic Web and realize the Web 3.0 vision. However, decentralization also renders KGs more prone to attacks with adverse effects on data integrity and query verifiability. While existing studies focus on ensuring data integrity, how to ensure query verifiability - thus guarding against incorrect, incomplete, or outdated query results - remains unsolved. We propose VeriDKG, the first SPARQL query engine for decentralized knowledge graphs (DKG) that offers both data integrity and query verifiability guarantees. The core of VeriDKG is the RGB-Trie, a new blockchain-maintained authenticated data structure (ADS) facilitating correctness proofs for SPARQL query results. VeriDKG enables verifiability of subqueries by gathering global index information on subgraphs using the RGB-Trie, which is implemented as a new variant of the Merkle prefix tree with an RGB color model. To enable verifiability of the final query result, the RGB-Trie is integrated with a cryptographic accumulator to support verifiable aggregation operations. A rigorous analysis of query verifiability in VeriDKG is presented, along with evidence from an extensive experimental study demonstrating its state-of-the-art query performance on the largeRDFbench benchmark.

Graph neural networks (GNNs) are a specialized type of deep learning models on graphs by learning aggregations over neighbor nodes. However, recent studies reveal that the performance of GNNs are severely deteriorated by injecting adversarial examples. Hence, improving the robustness of GNNs is of significant importance. Prior works are devoted to reducing the influence of direct adversaries which are adversarial attacks by positioning a node's one-hop neighbors, yet these approaches are limited in protecting GNNs from indirect adversarial attacks within a node's multi-hop neighbors. In this work, we approach this problem from a new angle by exploring the graph Ricci curvature, which can characterize the relationships of both direct and indirect links from any two nodes’ neighborhoods in the Riemannian space. We first investigate the distinguishable properties of adversarial attacks with graph Ricci curvature distribution. Then, a novel defense framework called Cure-GNN is proposed to detect and mitigate adversarial effects. Cure-GNN discerns the distinction between adversarial edges and normal edges via computing curvature, and merges it into the node features reconstructed by a residual learning framework. Extensive experiments over real-world datasets on node classification task demonstrate the efficacy of Cure-GNN and achieves superiority to the state-of-the-arts without incurring high complexity.

Blockchain has been regarded as a trusted carrier for distributed data storage. With large volumes of valuable data stored on blockchain, data query has become a major requirement. However, the existing blockchains do not provide efficient query functionality because of their deep-rooted chain structure. Blockchain database is a new direction that constructs index on top of blockchain to provide rich query functionalities. The existing works are either insecure because the query process separates from the blockchain consensus, or inscalable because all the data needs to be stored in the block. In this paper, we propose a novel semantic blockchain database called MSTDB. We design a hybrid on/off chain blockchain storage architecture in which the majority of blockchain storage is offloaded to the off-chain storage and a novel index structure named Merkle Semantic Trie (MST) is designed to be a secure and semantic bridge between on- and off-chain. Based on MST, MSTDB provides a variety of semantic query functions including multi-keyword query, range query, Top-K query, and cross-chain query. To improve the performance further, we design some index compression and query preprocessing techniques for MSTDB. Extensive experiments demonstrate the effectiveness and efficiency of our blockchain database.

Cross-heterogeneous blockchain interactions have been attracting much attention due to their application in depository blockchains mutual access and cross-blockchain identity authentication. Trusted access across heterogeneous chains is gradually becoming a hot challenge. In order to ensure cross-blockchain trusted access, the majority of the current works focus on on-chain notaries and the relay chain model. However, these methods have the following drawbacks: 1) notaries on the chain are more vulnerable to attacks due to their high degree of centralization, which causes off-chain users to lose their trust and thus exacerbates the off-chain trust crisis; 2) although the relay model involves multiple parties in maintenance and supervision and enjoys a more robust trust, the paticipatant nodes are relatively fixed, which impose a terrible dilemma that invalid nodes cannot participate in consensus formation in a timely manner, thus progressively disrupting the connectivity of the relay across heterogeneous chains and eventually reducing the rate of trusted mutual access. In this article, we propose a novel general framework for cross-heterogeneous blockchain communication based on a periodical committee rotation mechanism to support information exchange of diverse transactions across multiple heterogeneous blockchain systems. Connecting heterogeneous blockchains through committees has a more robust trust than the notary method. In order to eliminate the impact of downtime nodes in a timely manner, we periodically reorganize the committee and give priority to replacing downed nodes to ensure the reliability of the system. In addition, a message-oriented verification mechanism is designed to improve the rate of trusted intervisit across heterogeneous chains. We have built a prototype of the scheme and conducted simulation experiments on the current mainstream blockchain for message exchange across heterogeneous chains. The results show that our solution has a good performance both in inter-chain access rate and system stability.

Human Activity Recognition (HAR) plays an irreplaceable role in various applications such as security, gaming, and assisted living. Recent studies introduce deep learning to mitigate the manual feature extraction (i.e., data representation) efforts and achieve high accuracy. However, there are still challenges in learning accurate representations for sensory data due to the weakness of representation modules and the subject variances. We propose a scheme called Distance-based HAR from Ensembled spatial-temporal Representations (DHARER) to address above challenges. The idea behind DHARER is straightforward—the same activities should have similar representations. We first learn representations of the input sensory segments and latent prototype representations of each class, using a Convolution Neural Network (CNN)-based dual-stream representation module; then the learned representations are projected to activity types by measuring their similarity to the learned prototypes. We have conducted extensive experiments under a strict subject-independent setting on three large-scale datasets to evaluate the proposed scheme, and our experimental results demonstrate superior performance of DHARER to several state-of-the-art methods.

As a decentralized trusted database, the blockchain is finding applications in a growing number of fields such as finance, supply chain and medicine traceability, where large volumes of valuable data are stored on the blockchain. Currently, the mainstream blockchains employ a hybrid data storage architecture combining on-chain and off-chain storage. Real-time distributed search of mass data stored in this hybrid system is now a major need. However, previous fast retrieval schemes for the blockchain system are aimed only at on-chain data without considering their relevance to off-chain data, and thus fail to meet the requirement. In this paper, we propose an efficient blockchain data query scheme by introducing a novel Merkle Semantic Trie-based indexing technique without modifying the underlying database. A consensus on-chain index structure is constructed using the extracted semantic information of the off-chain data to create a mapping between the on-chain and off-chain data, thus enabling real-time data query both on and off the chain. Our scheme also provides multiple complex analytical query primitives to support semantic query, range query, and even fuzzy query. Experiments on three open data sets show that the proposed scheme has good query performance with shorter query latency for four different search types and offers better retrieval performance and verification efficiency than those available.

Compared with individual recommendation, recommending services to a group of users is more complicated because of various users' preference should be considered and introduces new challenging such as fairness, which has never been well studied in current works. In this paper, we propose a novel recommendation scheme called PFGR, which combines a probabilistic model with coalition game strategy, to ensure the accuracy and fairness between groups of users. Given a group of users and a set of services, PFGR models a generative process for service selection in light of several observations: 1) each group is related with several topics; 2) users' decisions on the service selection depends on their expertise, the opinions of members they are familiar with, and group influence; 3) each group contains active users and inactive user, whose activeness contributes to the existence of group. PFGR first estimates the preference of each user on a candidate service via combining user's expertise, inherent connection, and group influence. Then, it determines a group's decision on a service by aggregating the preference of group members using adaptive weights. Finally, PFGR considers users' activeness and employs a strategy based on coalition game to produce a ranked list which is fair to each group member as much as possible. Experimental results on three real-world datasets validate that PFGR can achieve higher Hit Rate and Average Reciprocal Hit Rank than state-of-the-art approaches, which indicates that PFGR attains both the precision and fairness of recommendation.