High-Confidence Computing最新文献

To solve the current situation of low vehicle-to-pile ratio, charging pile (CP) operators incorporate private CPs into the shared charging system. However, the introduction of private CP has brought about the problem of poor service quality. Reputation is a common service evaluation scheme, in which the third-party reputation scheme has the issue of single point of failure; although the blockchain-based reputation scheme solves the single point of failure issue, it also brings the challenges of storage and query efficiency. It is a feasible solution to classify and store information on multiple chains, and at this time, reputation needs to be calculated in a cross-chain mode. Crosschain reputation calculation faces the problems of correctness verification, integrity verification and efficiency. Therefore, this paper proposes a verifiable and efficient cross-chain calculation model for CP reputation. Specially, in this model, we propose a verifiable cross-chain contract calculation scheme that adopts polynomial commitment to solve the problems of polynomial damage and tampering that may be encountered in the crosschain process of outsourced polynomials, so as to ensure the integrity and correctness of polynomial calculations. In addition, the miner selection and incentive mechanism algorithm in this scheme ensures the correctness of extracted information when the outsourced polynomial is calculated on the blockchain. The security analysis and experimental results demonstrate that this scheme is feasible in practice.

Visual Dialog is a multi-modal task involving both computer vision and dialog systems. The goal is to answer multiple questions in conversation style, given an image as the context. Neural networks with attention modules are widely used for this task, because of their effectiveness in reasoning the relevance between the texts and images. In this work, we study how to further improve the quality of such reasoning, which is an open challenge. Our baseline is the Recursive Visual Attention (RVA) model, which refines the vision-text attention by iteratively visiting the dialog history. Building on top of that, we propose to improve the attention mechanism with contrastive learning. We train a Matching-Aware Attention Kernel (MAAK) by aligning the deep feature embeddings of an image and its caption, to provide better attention scores. Experiments show consistent improvements from MAAK. In addition, we study the effect of using Multimodal Compact Bilinear (MCB) pooling as a three-way feature fusion for the visual, textual and dialog history embeddings. We analyze the performance of both methods in the discussion section, and propose further ideas to resolve current limitations.

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.

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.

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.

With the rapid development of information technology, information system security and insider threat detection have become important topics for organizational management. In the current network environment, user behavioral bio-data presents the characteristics of nonlinearity and temporal sequence. Most of the existing research on authentication based on user behavioral biometrics adopts the method of manual feature extraction. They do not adequately capture the nonlinear and time-sequential dependencies of behavioral bio-data, and also do not adequately reflect the personalized usage characteristics of users, leading to bottlenecks in the performance of the authentication algorithm. In order to solve the above problems, this paper proposes a Temporal Convolutional Network method based on an Efficient Channel Attention mechanism (ECA-TCN) to extract user mouse dynamics features and constructs an one-class Support Vector Machine (OCSVM) for each user for authentication. Experimental results show that compared with four existing deep learning algorithms, the method retains more adequate key information and improves the classification performance of the neural network. In the final authentication, the Area Under the Curve (AUC) can reach 96%.

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.

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.

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.

Reliable and accessible cloud applications are essential for the future of ubiquitous computing, smart appliances, and electronic health. Owing to the vastness and diversity of the cloud, a most cloud services, both physical and logical services have failed. Using currently accessible traces, we assessed and characterized the behaviors of successful and unsuccessful activities. We devised and implemented a method to forecast which jobs will fail. The proposed method optimizes cloud applications more efficiently in terms of resource usage. Using Google Cluster, Mustang, and Trinity traces, which are publicly available, an in-depth evaluation of the proposed model was conducted. The traces were also fed into several different machine learning models to select the most reliable model. Our efficiency analysis proves that the model performs well in terms of accuracy, F1-score, and recall. Several factors, such as failure of forecasting work, design of scheduling algorithms, modification of priority criteria, and restriction of task resubmission, may increase cloud service dependability and availability.