High-Confidence Computing最新文献

Spider monkey optimization (SMO) is a quite popular and recent swarm intelligence algorithm for numerical optimization. SMO is Fission-Fusion social structure based algorithm inspired by spider monkey’s behavior. The algorithm proves to be very efficient in solving various constrained and unconstrained optimization problems. This paper presents the application of SMO in fog computing. We propose a heuristic initialization based spider monkey optimization algorithm for resource allocation and scheduling in a fog computing network. The algorithm minimizes the total cost (service time and monetary cost) of tasks by choosing the optimal fog nodes. Longest job fastest processor (LJFP), shortest job fastest processor (SJFP), and minimum completion time (MCT) based initialization of SMO are proposed and compared with each other. The performance is compared based on the parameters of average cost, average service time, average monetary cost, and the average cost per schedule. The results demonstrate the efficacy of MCT-SMO as compared to other heuristic initialization based SMO algorithms and Particle Swarm Optimization (PSO).

Edge intelligence is an emerging technology that enables artificial intelligence on connected systems and devices in close proximity to the data sources. decentralized collaborative learning (DCL) is a novel edge intelligence technique that allows distributed clients to cooperatively train a global learning model without revealing their data. DCL has a wide range of applications in various domains, such as smart city and autonomous driving. However, DCL faces significant challenges in ensuring its trustworthiness, as data isolation and privacy issues make DCL systems vulnerable to adversarial attacks that aim to breach system confidentiality, undermine learning reliability or violate data privacy. Therefore, it is crucial to design DCL in a trustworthy manner, with a focus on security, robustness, and privacy. In this survey, we present a comprehensive review of existing efforts for designing trustworthy DCL systems from the three key aformentioned aspects: security, robustness, and privacy. We analyze the threats that affect the trustworthiness of DCL across different scenarios and assess specific technical solutions for achieving each aspect of trustworthy DCL (TDCL). Finally, we highlight open challenges and future directions for advancing TDCL research and practice.

The vehicular edge computing (VEC) is a new paradigm that allows vehicles to offload computational tasks to base stations (BSs) with edge servers for computing. In general, the VEC paradigm uses the 5G for wireless communications, where the massive multi-input multi-output (MIMO) technique will be used. However, considering in the VEC environment with many vehicles, the energy consumption of BS may be very large. In this paper, we study the energy optimization problem for the massive MIMO-based VEC network. Aiming at reducing the relevant BS energy consumption, we first propose a joint optimization problem of computation resource allocation, beam allocation and vehicle grouping scheme. Since the original problem is hard to be solved directly, we try to split the original problem into two subproblems and then design a heuristic algorithm to solve them. Simulation results show that our proposed algorithm efficiently reduces the BS energy consumption compared to other schemes.

The communication efficiency optimization, censorship resilience, and generation of shared randomness are inseparable from the threshold cryptography in the existing Byzantine Fault Tolerant (BFT) consensus. The membership in consensus in a blockchain scenario supports dynamic changes, which effectively prevents the corruption of consensus participants. Especially in cross-chain protocols, the dynamic access to different blockchains will inevitably bring about the demand for member dynamic. Most existing threshold cryptography schemes rely on redefined key shares, leading to a static set of secret sharing participants. In this paper, we propose a general approach to coupling blockchain consensus and dynamic secret sharing. The committee performs consensus confirmation of both dynamic secret sharing and transaction proposals. Our scheme facilitates threshold cryptography membership dynamic, thus underlying support for membership dynamic of threshold cryptography-based BFT consensus schemes. We instantiate a dynamic HotStuff consensus to demonstrate the effectiveness of the scheme. After the correctness and security proof, our scheme achieves the secrecy and integrity of the threshold key shares while ensuring consensus liveness and safety. Experimental results prove that our scheme obtains dynamic membership with negligible overhead.

The widely used devices (e.g. smartphones, recorders) equipped with microphones have posed a severe threat to confidential conversations. In this paper, we design an inaudible anti-eavesdropping method: UltraJam, to reduce the risk of unwanted and secret recordings. UltraJam uses the ultrasonic signal to mask conversation. By leveraging the nonlinear effect of microphone circuits, the adaptive ultrasonic signal can be recorded and demodulated into low-frequency which can effectively squash the sound. Based on the characteristics of the attenuation coefficient and frequency response, we construct a number of jamming signals with different bandwidths and designed a wideband signal injection array, meanwhile adaptively adjust the power at each bandwidth signal to cover more frequency bands and increase usage scenarios. To verify the security of the microphone jamming system, we also utilize several audio recovery methods to recover the raw signal from jamming noise. The experimental results show that less than 1% of the words are recognized in the jamming recording, and even with the audio recovery method, 99% of the words still cannot be recognized in the recovered jamming recording.

Food traceability is a critical factor that can ensure food safety for enhancing the credibility of the product, thus achieving heightened user satisfaction and loyalty. The Perishable Food SC (PFSC) requires paramount care for ensuring quality owing to the limited product life. The PFSC comprises of multiple organizations with varied interests and is more likely to be hesitant in sharing the traceability details among one another owing to a lack of trust, which can be overcome by using Blockchain (BC). In this research, an efficient scheme using BC-Deep Residual Network (BC-DRN) is developed to provide food traceability for dairy products. Here, food traceability is determined by using various modules, like the Internet of Things (IoT), BC data management, Food traceability BC architecture, and DRN-based food quality evaluation modules. The devised BC-DRN-based food quality traceability system is examined based on its performance metrics, like sensitivity, response time, and testing accuracy, and it has attained better values of 0.939, 109.564 s, and 0.931.

As one of the most promising machine learning frameworks emerging in recent years, Federated learning (FL) has received lots of attention. The main idea of centralized FL is to train a global model by aggregating local model parameters and maintain the private data of users locally. However, recent studies have shown that traditional centralized federated learning is vulnerable to various attacks, such as gradient attacks, where a malicious server collects local model gradients and uses them to recover the private data stored on the client. In this paper, we propose a decentralized federated learning against aTtacks (DEFEAT) framework and use it to defend the gradient attack. The decentralized structure adopted by this paper uses a peer-to-peer network to transmit, aggregate, and update local models. In DEFEAT, the participating clients only need to communicate with their single-hop neighbors to learn the global model, in which the model accuracy and communication cost during the training process of DEFEAT are well balanced. Through a series of experiments and detailed case studies on real datasets, we evaluate the excellent model performance of DEFEAT and the privacy preservation capability against gradient attacks.

As the promising next-generation power grid, the smart grid has developed rapidly in recent years. The smart grid enables energy to be stored and delivered more efficiently and safely, but user data’s integrity protection has been an important security issue in the smart grid. Although lots of digital signature protocols for the smart grid have been proposed to resolve this problem, they are vulnerable to quantum attacks. To deal with this problem, an efficient identity-based signature protocol on lattices is proposed in this paper. To improve our protocol’s efficiency, the tree of commitments is utilized. Moreover, a detailed performance evaluation of the proposed protocol is made. The performance analysis demonstrates that the potential utility of our protocol in the smart grid is huge.

The cloud boundary network environment is characterized by a passive defense strategy, discrete defense actions, and delayed defense feedback in the face of network attacks, ignoring the influence of the external environment on defense decisions, thus resulting in poor defense effectiveness. Therefore, this paper proposes a cloud boundary network active defense model and decision method based on the reinforcement learning of intelligent agent, designs the network structure of the intelligent agent attack and defense game, and depicts the attack and defense game process of cloud boundary network; constructs the observation space and action space of reinforcement learning of intelligent agent in the non-complete information environment, and portrays the interaction process between intelligent agent and environment; establishes the reward mechanism based on the attack and defense gain, and encourage intelligent agents to learn more effective defense strategies. the designed active defense decision intelligent agent based on deep reinforcement learning can solve the problems of border dynamics, interaction lag, and control dispersion in the defense decision process of cloud boundary networks, and improve the autonomy and continuity of defense decisions.

Software vulnerabilities pose significant risks to computer systems, impacting our daily lives, productivity, and even our health. Identifying and addressing security vulnerabilities in a timely manner is crucial to prevent hacking and data breaches. Unfortunately, current vulnerability identification methods, including classical and deep learning-based approaches, exhibit critical drawbacks that prevent them from meeting the demands of the contemporary software industry. To tackle these issues, we present JFinder, a novel architecture for Java vulnerability identification that leverages quad self-attention and pre-training mechanisms to combine structural information and semantic representations. Experimental results demonstrate that JFinder outperforms all baseline methods, achieving an accuracy of 0.97 on the CWE dataset and an F1 score of 0.84 on the PROMISE dataset. Furthermore, a case study reveals that JFinder can accurately identify four cases of vulnerabilities after patching.