Traditional reinforcement learning methodologies, primarily based on multi-layer perceptron (MLP) architectures, require extensive, fully connected layers for complex nonlinear representations. Such an approach increases computational demands and enhances the likelihood of model overfitting. In this paper, we present an innovative reinforcement learning approach, leveraging the Kolmogorov-Arnold Networks (KAN) framework, to enhance decision-making processes and resource management strategies in edge networks. We develop a KAN-based hybrid proximal policy optimization algorithm (KANH-PPO) to address this issue. This algorithm effectively addresses the challenge of hybrid action spaces within edge networks, which include discrete action spaces characterized by computational offloading decisions and continuous action spaces characterized by power allocation. Furthermore, the KANH-PPO algorithm innovatively integrates the KAN architecture, significantly reducing the number of training parameters and enhancing the algorithm's fitting capability and overall performance. Simulation experiments indicate that our proposed KANH-PPO algorithm outperforms the benchmark algorithm in terms of convergence speed and edge network system power, and it requires significantly fewer training parameters than benchmark algorithms. This helps to reduce the power consumption of communication and promote the development of green communication.

The implementation of the Internet of Things (IoT) technology has the potential to unleash the capabilities of generative artificial intelligence (GAI). However, integrating GAI with IoT introduces a significant challenge in managing the limited resources of edge networks. In this article, we propose a resource optimization framework for GAI in IoT systems to address this issue, leveraging a heterogeneous computing framework. We focus on the system utility maximization problem, which jointly optimizes transmit power, heterogeneous computing allocation, CPU-cycle frequency, GPU-cycle frequency, and task scheduling under the latency constraint. The optimal CPU-cycle frequency, GPU-cycle frequency, and computing allocation are obtained by employing data parallelism analysis. In particular, we develop a hierarchical soft actor-critic with an intrinsic curiosity (HSAC-IC) algorithm to determine the task scheduling strategy. The HSAC-IC algorithm utilizes a hierarchical strategy structure and an intrinsic curiosity module (ICM) to improve learning efficiency and performance, particularly in environments characterized by sparse rewards, high-dimensional action spaces, and complex tasks. Our simulations benchmark the HSAC-IC algorithm against two existing deep reinforcement learning (DRL) algorithms and three reference schemes. The results illustrate that our scheme significantly outperforms these alternatives, ensuring AIGC user service requirements, while minimizing service generation costs, and optimizing resource allocation by configuring the image quality strategy on edge servers.

As an emerging class of internet of vehicles, vehicular social networks (VSNs) provide passengers, drivers, and vehicles with extensive data sharing services to improve traffic congestion and road safety. However, the insecure transmissions of shared data may disclose sensitive information, such as private data, location, and driving route. Although attribute-based encryption (ABE) is a promising technology to enable secure data sharing, the existing ABE solutions applied to VSNs encounter three-fold deficiencies: (1) the shared data stored in vehicular cloud server would be leaked in the event of key compromise; (2) relying on one or more fully trusted entities to generate keys for vehicles through secure channels; (3) private information leakage and misbehavior of data user vehicles are neglected. Motivated by these challenges, this paper proposes a puncturable registered ABE scheme called PR-ABE for VSNs with enhanced security and practicality. To be specific, our PR-ABE achieves flexible access control and precise data deletion. The former ensures that only registered vehicles with authorized attributes can obtain the shared data. The latter prevents data disclosure when key compromise happens. Meanwhile, PR-ABE enables vehicles to generate keys independently and eliminates the need for any fully trusted authority. In addition, hidden policy and traceability are fulfilled in PR-ABE to protect private information and deal with malicious vehicles, respectively. Finally, the rigorous security proof and performance evaluation demonstrate that PR-ABE is a practical and efficient solution.

With the continuous development of digitization evolutions, vehicular digital twin networks (VDTNs) facilitate traffic data and optimization results to be exchanged between the vehicle and digital twin as well as shared among a group of digital twins. However, the data exchange and group sharing processes take place in real-time over public communication channels, which suffer from various security and privacy threats. Key agreement technologies are promising to enable secure data communications for entities, but the existing key agreement schemes generally fail to fulfill the requirements of synchronization, privacy, and entity management for VDTNs. Therefore, we propose a blockchain-assisted privacy-preserving and synchronized key agreement scheme for VDTNs. In the proposed scheme, the anonymous vehicle and digital twin can negotiate a secret session key in the case of synchronization to achieve secure data exchange. Meanwhile, digital twins are capable of utilizing synchronized state information to dynamically establish a common group encryption key but hold individual decryption keys, which guarantee the security of group sharing. Additionally, the proposed scheme is able to protect identity privacy and manage vehicles and digital twins with the assistance of blockchain and smart contract. The security analysis demonstrates that the proposed scheme provides security and privacy assurances for VDTNs. The performance evaluation indicates that it has excellent expressions in terms of efficiency, practicality, and smart contract consumption.

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.

Community detection refers to mechanisms that aim to identify groups of interacting nodes in a network according to the structural properties of the network. It has been used to analyze various graphs. In the context of social networks, it requires the collection of each user's social relations, posing the risk of user privacy intrusion caused by untrusted servers. Local differential privacy is a widely adopted approach for providing privacy protection while allowing acceptable utility of the protected data for analytics. There has been growing research interest in applying local differential privacy protection to community detection. However, such protection approaches typically suffer from poor accuracy due to the excessive noise in the protected data. This paper proposes LDP-Cd, a two-phase community detection framework under local differential privacy. LDP-Cd initializes the community groups using the Louvain community detection algorithm and iteratively refines the community in the second phase. Besides, we propose an order-consistent data perturbation method over the degree vector, thus ensuring the ordering consistency of the fitness between the user and community groups, thereby improving the accuracy of community detection. Experimental results on real datasets show that LDP-Cd has significant advantages over existing methods regarding community detection accuracy and a trade-off between user privacy and community detection utility.

Using behaviour association or dependency to detect malicious code can improve the recognition rate of malicious code. A malicious code detection method based on precise behaviour dependency graph (PBDG) is proposed. We create a stain file index by filtering the stain source blacklist, which not only saves storage space, but also quickly locates instructions. An active variable path verification algorithm is proposed to verify and purify the Source → Sink path. The PBDG and its matching algorithm are constructed to identify the malicious code family of the source program. The experimental results on six data sets show the effectiveness of this method. The introduction of active variable paths reduces the number of paths that need to be traversed by 91.2% at most. In terms of the detection effect of malicious code, especially for web applications, it has a good detection accuracy and a low false positive rate.

In the Cyber-Physical-Social System (CPSS), mobile service applications share and exchange data in the cyberspace and physical world. With the explosive growth of data, cloud storage service is introduced as it has broken through the limitations of local storage space. However, since cloud storage servers may remove some data to deceive users to save space, it is important to check the integrity of data in cloud storage servers. Most existing verification schemes support users to delegate a semi-trusted entity third-party auditor (TPA) to audit the stored data publicly, but it may result in user data security risks for its interests. The security risk is one aspect, what is worse, the high overhead of auditing also limits the the practicality of auditing. To tackle the issues, we put forward a secure dynamic public audit scheme based on blockchain and a red-black tree structure. Unlike relying on any single TPA, every user on the blockchain can act as an auditor to achieve public auditing. Secondly, based on the red-black tree, a new storage structure is proposed to store data signatures, which achieves efficient data storage and auditing. Based on the raised prototype system, we prove the security of our scheme and implement it on Hyperledger Fabric. Many experiments indicate that the scheme achieves the expected efficacy.

Abstract Collecting and analysing customers' data plays an essential role in the more intense market competition. It is critical to perform data analysis effectively while ensuring the user's privacy, especially after various privacy regulations are enacted. In this paper, we consider the problem of aggregating the stream data generated from wearable devices in a specific time period in a privacy‐preserving manner. Specifically, we adopt the local differential privacy mechanism to provide a strong privacy guarantee for users. One major challenge is that all values of the stream need to be perturbed. The additive noise makes it hard to release an accurate data stream. One way to reduce the noise scale is to select some data points to perturb instead of all. The intuition is that more privacy budgets are applied to a single data point, which ensures the statistical accuracy. The perturbed data points are used to predict the un‐selected data points without consuming an extra privacy budget. Based on this idea, we propose a novel stream data statistical framework, which includes four components, data fitting, skeleton point selection, noisy stream generation, and data aggregation. Extensive experiment results show that our proposed method achieves a much smaller mean square error given a fixed privacy budget compared with the state‐of‐the‐art.

As a result of the rapid development of Internet of Things (IoT) systems, an increasing number of academics are focusing on finding new applications for IoT systems. For IoT systems, crowdsourcing is a prevalent practise. Due to the large number of deployed devices in IoT networks, more research is still required on the privacy and trust issues that arise when utilizing crowdsourcing. As a result of the characteristics of social computing, the crowdsourcing network poses issues in terms of confidentiality and reliability. To consolidate and create this industry, we have built a differentially private crowdsourcing system that integrates public and private blockchains to address the privacy and trust issues of conventional crowdsourcing systems. Our proposed solution enables varying levels of privacy protection to protect the user’s identity and location. Moreover, the installation of blockchain networks might potentially ensure the data’s integrity. In the conclusion of this article, the possibility of deploying a crowdsourcing system with blockchain in IoE networks is examined.

In order to remain competitive, Internet companies collect and analyse user data for the purpose of the improvement of user experiences. Frequency estimation is a widely used statistical tool, which could potentially conflict with the relevant privacy regulations. Privacy preserving analytic methods based on differential privacy have been proposed, which require either a large user base or a trusted server. Although the requirements for such solutions may not be a problem for larger companies, they may be unattainable for smaller organizations. To address this issue, we propose a distributed privacy-preserving sampling-based frequency estimation method which has high accuracy even in the scenario with a small number of users while not requiring any trusted server. This is achieved by combining multi-party computation and sampling techniques. We also provide a relation between its privacy guarantee, output accuracy, and the number of participants. Distinct from most existing methods, our methods achievecentralizeddifferential privacy guarantee without the need of any trusted server. We established that, even for a small number of participants, our mechanisms can produce estimates with high accuracy and hence they provide smaller companies with more opportunity for growth through privacy-preserving statistical analysis. We further propose an architectural model to support weighted aggregation in order to achieve a higher accuracy estimate to cater for users with varying privacy requirements. Compared to the unweighted aggregation, our method provides a more accurate estimate. Extensive experiments are conducted to show the effectiveness of the proposed methods.

Using the features of malicious family to detect malicious code can improve the analysis efficiency and reduce the workload. Aiming at the problems of low efficiency and low accuracy of classifiers in analyzing and detecting malicious code using traditional machine learning, a new malicious family identification method 2MFI-FT is proposed. Firstly, the more comprehensive and essential features of malicious code are obtained by extracting local feature information, assembly instruction set information and visible string information. Secondly, in order to solve the problem of inconsistent images generated by feature sequences, different feature grayscale images are fused into a multi-channel mapping feature image (2MFI) based on the signature matrix. Thirdly, in view of the high cost of collecting and labeling enough data, a classification model with high recognition accuracy and strong generalization ability is realized, based on the fine-tuned Convolutional Neural Network (CNN). The regularization technique is also used to improve the robustness of the model. It is tested on Microsoft Malware Classification Challenge dataset. The experimental results show that the proposed 2MFI method for multi-channel feature image visualization has good identification effect and low time consumption when used as the input of the network model. At the same time, the 2MFI-FT method combined with fine-tuned CNN can accurately identify malicious families, and the accuracy on small training sets and large training sets can reach about 98.25% and 99.68% respectively, which provides a feasible solution for effective identification of malicious families.

Privacy-preserving data analysis is an emerging area that addresses the dilemma of performing data analysis on user data while protecting users’ privacy. In this paper, we consider the problem of constructing privacy-preservingK-means clustering protocol for data analysis that provides local privacy to users’ data. To enable a desirable degree of local privacy guarantee while maintaining high accuracy of the clustering, we adopt a generalized differential privacy definition,dχ-privacy, which quantifies the distinguishability level based on the distance between data records defined by the distance functiondχ. In our work, we consider the space of data points as a metric space imbued with Euclidean distance and propose a bounded perturbation mechanism (BPM) with bounded sampling space of the perturbed data points, which is formally shown to achievedχ-privacy. BPM perturbs the data as a whole instead of treating each dimension independently, which is desirable since the privacy budget is no longer required to be split among different dimensions. Bounded output space also means that we will not get into the case where the report or the statistical result is so far out of the data domain that it is hard to interpret. Furthermore, it can also help in limiting the amount of bandwidth needed to send such report to the server. The design of BPM is based on a probability density function which decreases exponentially as the Euclidean distance with respect to the true value grows. It is also designed with the aim of ensuring that BPM produces perturbed data that provides the claimed privacy guarantee while ensuring high utility response. To guarantee the efficiency of the perturbation method, we propose an efficient algorithm to sample from the proposed distribution and apply BPM to the design ofdχ-privateK-means clustering algorithms. Lastly, we analyse the privacy and utility guarantee provided by the proposed method and provide its experimental results.

Crowdsourcing plays an essential role in the Internet of Things (IoT) for data collection, where a group of workers is equipped with Internet-connected geolocated devices to collect sensor data for marketing or research purpose. In this article, we consider crowdsourcing these worker's hot travel path. Each worker is required to report his real-time location information, which is sensitive and has to be protected. Encryption-based methods are the most direct way to protect the location, but not suitable for resource-limited devices. Besides, local differential privacy is a strong privacy concept and has been deployed in many software systems. However, the local differential privacy technology needs a large number of participants to ensure the accuracy of the estimation, which is not always the case for crowdsourcing. To solve this problem, we proposed a trie-based iterative statistic method, which combines additive secret sharing and local differential privacy technologies. The proposed method has excellent performance even with a limited number of participants without the need of complex computation. Specifically, the proposed method contains three main components: iterative statistics, adaptive sampling, and secure reporting. We theoretically analyze the effectiveness of the proposed method and perform extensive experiments to show that the proposed method not only provides a strict privacy guarantee, but also significantly improves the performance from the previous existing solutions.

The Internet of Vehicles (IoV) is a promising branch of the Internet of Things. IoV simulates a large variety of crowdsourcing applications, such as Waze, Uber, and Amazon Mechanical Turk, etc. Users of these applications report the real-time traffic information to the cloud server which trains a machine learning model based on traffic information reported by users for intelligent traffic management. However, crowdsourcing application owners can easily infer users' location information, traffic information, motor vehicle information, environmental information, etc., which raises severe sensitive personal information privacy concerns of the users. In addition, as the number of vehicles increases, the frequent communication between vehicles and the cloud server incurs unexpected amount of communication cost. To avoid the privacy threat and reduce the communication cost, in this article, we propose to integrate federated learning and local differential privacy (LDP) to facilitate the crowdsourcing applications to achieve the machine learning model. Specifically, we propose four LDP mechanisms to perturb gradients generated by vehicles. The proposed Three-Outputs mechanism introduces three different output possibilities to deliver a high accuracy when the privacy budget is small. The output possibilities of Three-Outputs can be encoded with two bits to reduce the communication cost. Besides, to maximize the performance when the privacy budget is large, an optimal piecewise mechanism (PM-OPT) is proposed. We further propose a suboptimal mechanism (PM-SUB) with a simple formula and comparable utility to PM-OPT. Then, we build a novel hybrid mechanism by combining Three-Outputs and PM-SUB. Finally, an LDP-FedSGD algorithm is proposed to coordinate the cloud server and vehicles to train the model collaboratively. Extensive experimental results on real-world data sets validate that our proposed algorithms are capable of protecting privacy while guaranteeing utility.

In privacy-preserving machine learning, individual parties are reluctant to share their sensitive training data due to privacy concerns. Even the trained model parameters or prediction can pose serious privacy leakage. To address these problems, we demonstrate a generally applicable Distributed Privacy-Preserving Prediction (DPPP) framework, in which instead of sharing more sensitive data or model parameters, an untrusted aggregator combines only multiple models' predictions under provable privacy guarantee. Our framework integrates two main techniques to guarantee individual privacy. First, we introduce the improved Binomial Mechanism and Discrete Gaussian Mechanism to achieve distributed differential privacy. Second, we utilize homomorphic encryption to ensure that the aggregator learns nothing but the noisy aggregated prediction. Experimental results demonstrate that our framework has comparable performance to the non-private frameworks and delivers better results than the local differentially private framework and standalone framework.