With the advancement of deep learning techniques, the number of model parameters has been increasing, leading to significant memory consumption and limits in the deployment of such models in real-time applications. To reduce the number of model parameters and enhance the generalization capability of neural networks, we propose a method called Decoupled MetaDistil, which involves decoupled meta-distillation. This method utilizes meta-learning to guide the teacher model and dynamically adjusts the knowledge transfer strategy based on feedback from the student model, thereby improving the generalization ability. Furthermore, we introduce a decoupled loss method to explicitly transfer positive sample knowledge and explore the potential of negative samples knowledge. Extensive experiments demonstrate the effectiveness of our method.

Currently, important privacy data of the Internet of Things (IoT) face extremely high risks of leakage. Attackers persistently engage in continuous attacks on terminal devices to obtain private data of crucial importance. Although significant progress has been made in recent years in deep reinforcement learning defense strategies, most defense methods still face problems such as low defense resource allocation efficiency and insufficient defense coordination capabilities. To solve the above problems, this paper constructs a novel adversarial security scenario and proposes a security game model that integrates defense resource allocation and patrol inspection. Regarding the above game model, this paper designs a deep reinforcement learning algorithm named SDSA to calculate its security defense strategy. SDSA calculates the allocation strategy of the best patrolling strategy that is most suitable for the defender by searching the policy on a multi-dimensional discrete action space, and enables multiple defense agents to cooperate efficiently by training a multi-intelligent Dueling Double Deep Q-Network (D3QN) with prioritized experience replay. Finally, the experimental results show that the SDSA-learned security defense strategy can provide a feasible and effective security protection strategy for defenders against attacks compared to the MADDPG and OptGradFP methods.

A redactable blockchain allows authorized individuals to remove or replace undesirable content, offering the ability to remove illegal or unwanted information. Access control is a mechanism that limits data visibility and ensures that only authorized users can decrypt and access encrypted information, playing a crucial role in addressing privacy concerns and securing the data stored on a blockchain. Redactability and access control are both essential components when implementing a regulated consortium blockchain in real-world situations to ensure the secure sharing of data while removing undesirable content. We propose a decentralized consortium blockchain system prototype that supports redactability and access control. Through the development of a prototype blockchain system, we investigate the feasibility of combining these approaches and demonstrate that it is possible to implement a redactable blockchain with access control in a consortium blockchain setting.

Nowadays, Flying Adhoc Networks play a vital role due to its high efficiency in fast communication. Unmanned aerial vehicles transmit data much faster than other networks and are useful in all aspects of communication. In healthcare applications, wireless body area network transmits the data, whereas the security, which is the most important concern to be focused in a flying adhoc network is not satisfactory. Many intruders tamper the network, degrading the overall network performance. To avoid security issues, a unique and secure routing protocol that provides a single solution for five different types of attacks such as, black hole attacks, grey hole attacks, yoyo attacks, conjoint attack and jamming attacks, is proposed. The simulation results analyses the network performance by using the proposed routing table. In comparison to the other solutions rendered to resolve the affected network, this proposed routing protocol has a higher throughput, higher delivery rate, and lower delay. The Unique and Secure Routing Protocol (USRP) provides an integrated solution for an efficient and secure communication in a flying adhoc network.

Autonomous vehicles in industrial parks can provide intelligent, efficient, and environmentally friendly transportation services, making them crucial tools for solving internal transportation issues. Considering the characteristics of industrial park scenarios and limited resources, designing and implementing autonomous driving solutions for autonomous vehicles in these areas has become a research hotspot. This paper proposes an efficient autonomous driving solution based on path planning, target recognition, and driving decision-making as its core components. Detailed designs for path planning, lane positioning, driving decision-making, and anti-collision algorithms are presented. Performance analysis and experimental validation of the proposed solution demonstrate its effectiveness in meeting the autonomous driving needs within resource-constrained environments in industrial parks. This solution provides important references for enhancing the performance of autonomous vehicles in these areas.

The privacy concern in smart contract applications continues to grow, leading to the proposal of various schemes aimed at developing comprehensive and universally applicable privacy-preserving smart contract (PPSC) schemes. However, the existing research in this area is fragmented and lacks a comprehensive system overview. This paper aims to bridge the existing research gap on PPSC schemes by systematizing previous studies in this field. The primary focus is on two categories: PPSC schemes based on cryptographic tools like zero-knowledge proofs, as well as schemes based on trusted execution environments. In doing so, we aim to provide a condensed summary of the different approaches taken in constructing PPSC schemes. Additionally, we also offer a comparative analysis of these approaches, highlighting the similarities and differences between them. Furthermore, we shed light on the challenges that developers face when designing and implementing PPSC schemes. Finally, we delve into potential future directions for improving and advancing these schemes, discussing possible avenues for further research and development.

Dynamic graph neural networks (DGNNs) have demonstrated their extraordinary value in many practical applications. Nevertheless, the vulnerability of DNNs is a serious hidden danger as a small disturbance added to the model can markedly reduce its performance. At the same time, current adversarial attack schemes are implemented on static graphs, and the variability of attack models prevents these schemes from transferring to dynamic graphs. In this paper, we use the diffused attack of node injection to attack the DGNNs, and first propose the node injection attack based on structural fragility against DGNNs, named Structural Fragility-based Dynamic Graph Node Injection Attack (SFIA). SFIA firstly determines the target time based on the period weight. Then, it introduces a structural fragile edge selection strategy to establish the target nodes set and link them with the malicious node using serial inject. Finally, an optimization function is designed to generate adversarial features for malicious nodes. Experiments on datasets from four different fields show that SFIA is significantly superior to many comparative approaches. When the graph is injected with 1% of the original total number of nodes through SFIA, the link prediction Recall and MRR of the target DGNN link decrease by 17.4% and 14.3% respectively, and the accuracy of node classification decreases by 8.7%.

Graph de-anonymization is a technique used to reveal connections between entities in anonymized graphs, which is crucial in detecting malicious activities, network analysis, social network analysis, and more. Despite its paramount importance, conventional methods often grapple with inefficiencies and challenges tied to obtaining accurate query graph data. This paper introduces a neural-based inexact graph de-anonymization, which comprises an embedding phase, a comparison phase, and a matching procedure. The embedding phase uses a graph convolutional network to generate embedding vectors for both the query and anonymized graphs. The comparison phase uses a neural tensor network to ascertain node resemblances. The matching procedure employs a refined greedy algorithm to discern optimal node pairings. Additionally, we comprehensively evaluate its performance via well-conducted experiments on various real datasets. The results demonstrate the effectiveness of our proposed approach in enhancing the efficiency and performance of graph de-anonymization through the use of graph embedding vectors.

Light Field (LF) depth estimation is an important research direction in the area of computer vision and computational photography, which aims to infer the depth information of different objects in three-dimensional scenes by capturing LF data. Given this new era of significance, this article introduces a survey of the key concepts, methods, novel applications, and future trends in this area. We summarize the LF depth estimation methods, which are usually based on the interaction of radiance from rays in all directions of the LF data, such as epipolar-plane, multi-view geometry, focal stack, and deep learning. We analyze the many challenges facing each of these approaches, including complex algorithms, large amounts of computation, and speed requirements. In addition, this survey summarizes most of the currently available methods, conducts some comparative experiments, discusses the results, and investigates the novel directions in LF depth estimation.

In autonomous driving systems, perception is pivotal, relying chiefly on sensors like LiDAR and cameras for environmental awareness. LiDAR, celebrated for its detailed depth perception, is being increasingly integrated into autonomous vehicles. In this article, we analyze the robustness of four LiDAR-included models against adversarial points under physical constraints. We first introduce an attack technique that, by simply adding a limited number of physically constrained adversarial points above a vehicle, can make the vehicle undetectable by the LiDAR-included models. Experiments reveal that adversarial points adversely affect the detection capabilities of both LiDAR-only and LiDAR-camera fusion models, with a tendency for more adversarial points to escalate attack success rates. Notably, voxel-based models are more susceptible to deception by these adversarial points. We also investigated the impact of the distance and angle of the added adversarial points on the attack success rate. Typically, the farther the victim object to be hidden and the closer to the front of the LiDAR, the higher the attack success rate. Additionally, we have experimentally proven that our generated adversarial points possess good cross-model adversarial transferability and validated the effectiveness of our proposed optimization method through ablation studies. Furthermore, we propose a new plug-and-play, model-agnostic defense method based on the concept of point smoothness. The ROC curve of this defense method shows an AUC value of approximately 0.909, demonstrating its effectiveness.

With the prevalence of various sensors and smart devices in people’s daily lives, numerous types of information are being sensed. While using such information provides critical and convenient services, we are gradually exposing every piece of our behavior and activities. Researchers are aware of the privacy risks and have been working on preserving privacy while sensing human activities. This survey reviews existing studies on privacy-preserving human activity sensing. We first introduce the sensors and captured private information related to human activities. We then propose a taxonomy to structure the methods for preserving private information from two aspects: individual and collaborative activity sensing. For each of the two aspects, the methods are classified into three levels: signal, algorithm, and system. Finally, we discuss the open challenges and provide future directions.

Multi-agent reinforcement learning holds tremendous potential for revolutionizing intelligent systems across diverse domains. However, it is also concomitant with a set of formidable challenges, which include the effective allocation of credit values to each agent, real-time collaboration among heterogeneous agents, and an appropriate reward function to guide agent behavior. To handle these issues, we propose an innovative solution named the Graph Attention Counterfactual Multiagent Actor-Critic algorithm (GACMAC). This algorithm encompasses several key components: First, it employs a multi-agent actor-critic framework along with counterfactual baselines to assess the individual actions of each agent. Second, it integrates a graph attention network to enhance real-time collaboration among agents, enabling heterogeneous agents to effectively share information during handling tasks. Third, it incorporates prior human knowledge through a potential-based reward shaping method, thereby elevating the convergence speed and stability of the algorithm. We tested our algorithm on the StarCraft Multi-Agent Challenge (SMAC) platform, which is a recognized platform for testing multi-agent algorithms, and our algorithm achieved a win rate of over 95% on the platform, comparable to the current state-of-the-art multi-agent controllers.

Compared to 2D imaging data, the 4D light field (LF) data retains richer scene’s structure information, which can significantly improve the computer’s perception capability, including depth estimation, semantic segmentation, and LF rendering. However, there is a contradiction between spatial and angular resolution during the LF image acquisition period. To overcome the above problem, researchers have gradually focused on the light field super-resolution (LFSR). In the traditional solutions, researchers achieved the LFSR based on various optimization frameworks, such as Bayesian and Gaussian models. Deep learning-based methods are more popular than conventional methods because they have better performance and more robust generalization capabilities. In this paper, the present approach can mainly divided into conventional methods and deep learning-based methods. We discuss these two branches in light field spatial super-resolution (LFSSR), light field angular super-resolution (LFASR), and light field spatial and angular super-resolution (LFSASR), respectively. Subsequently, this paper also introduces the primary public datasets and analyzes the performance of the prevalent approaches on these datasets. Finally, we discuss the potential innovations of the LFSR to propose the progress of our research field.