检索结果-南通市图书馆

Automated federated learning‐based adversarial attack and defence in industrial control systems

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

IET Cyber-Systems and Robotics 2024年第2期6卷 109-127页

作者： Guo-Qiang Zeng Jun-Min Shao Kang-Di Lu Guang-Gang Geng Jian Weng College of Cyber security Jinan UniversityGuangzhouChina National Joint Engineering Research Center of Network security Detection and Protection Technology Jinan UniversityGuangzhouChina College of Information Science and Technology Donghua UniversityShanghaiChina

With the development of deep learning and federated learning(FL),federated intrusion detection systems(IDSs)based on deep learning have played a significant role in securing industrial control systems(ICSs).However,adversarial attacks on ICSs may compromise the ability of deep learning-based IDSs to accurately detect cyberattacks,leading to serious ***,in the process of generating adversarial samples,the selection of replacement models lacks an effective method,which may not fully expose the vulnerabilities of the *** authors first propose an automated FL-based method to generate adversarial samples in ICSs,called AFL-GAS,which uses the prin-ciple of transfer attack and fully considers the importance of replacement models during the process of adversarial sample *** the proposed AFL-GAS method,a lightweight neural architecture search method is developed to find the optimised replacement model composed of a combination of four lightweight basic ***,to enhance the adversarial robustness,the authors propose a multi-objective neural archi-tecture search-based IDS method against adversarial attacks in ICSs,called MoNAS-IDSAA,by considering both classification performance on regular samples and adver-sarial robustness *** experimental results on three widely used intrusion detection datasets in ICSs,such as secure water treatment(SWaT),Water Distribution,and Power System Attack,demonstrate that the proposed AFL-GAS method has obvious advantages in evasion rate and lightweight compared with other four ***,the proposed MoNAS-IDSAA method not only has a better classification performance,but also has obvious advantages in model adversarial robustness compared with one manually designed federated adversarial learning-based IDS method.

关键词： adversarial attacks adversarial robustness automated federated learning Industrial control system intrusion

A New Method Based on Evolutionary Algorithm for Symbolic Network Weak Unbalance

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal on internet of Things 2019年第2期1卷 41-53页

作者： Yirong Jiang Weijin Jiang Jiahui Chen Yang Wang Yuhui Xu Lina Tan Liang Guo Tonghua Normal University Tonghua134002China Key laboratory of Hunan Province for New Retail Virtual Reality Technology Hunan University of CommerceChangsha410205China Institute of Big Data and internet Innovation Hunan University of CommerceChangsha410205China School of Computer Science and Technology Wuhan University of TechnologyWuhan430073China School of Bioinformatics University of MinnesotaTwin CitiesUSA

The symbolic network adds the emotional information of the relationship,that is,the“+”and“-”information of the edge,which greatly enhances the modeling ability and has wide application in many *** unbalance is an important indicator to measure the network *** paper starts from the weak structural equilibrium theorem,and integrates the work of predecessors,and proposes the weak unbalanced algorithm EAWSB based on evolutionary *** on the large symbolic networks Epinions,Slashdot and WikiElections show the effectiveness and efficiency of the proposed *** EAWSB,this paper proposes a compression-based indirect representation method,which effectively reduces the size of the genotype space,thus making the algorithm search more complete and easier to get better solutions.

关键词： Weak structural balance signed networks evolutionary algorithms incremental computation compressed representation

A Lightweight IoT Malware Detection and Family Classification Method

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer and Communications 2024年第4期12卷 201-227页

作者： Changguang Wang Ziqi Ma Qingru Li Dongmei Zhao Fangwei Wang College of Computer and Cyber security Hebei Normal University Shijiazhuang China Key laboratory of Network and Information security of Hebei Province Hebei Normal University Shijiazhuang China

A lightweight malware detection and family classification system for the internet of Things (IoT) was designed to solve the difficulty of deploying defense models caused by the limited computing and storage resources of IoT devices. By training complex models with IoT software gray-scale images and utilizing the gradient-weighted class-activated mapping technique, the system can identify key codes that influence model decisions. This allows for the reconstruction of gray-scale images to train a lightweight model called LMDNet for malware detection. Additionally, the multi-teacher knowledge distillation method is employed to train KD-LMDNet, which focuses on classifying malware families. The results indicate that the model’s identification speed surpasses that of traditional methods by 23.68%. Moreover, the accuracy achieved on the Malimg dataset for family classification is an impressive 99.07%. Furthermore, with a model size of only 0.45M, it appears to be well-suited for the IoT environment. By training complex models using IoT software gray-scale images and utilizing the gradient-weighted class-activated mapping technique, the system can identify key codes that influence model decisions. This allows for the reconstruction of gray-scale images to train a lightweight model called LMDNet for malware detection. Thus, the presented approach can address the challenges associated with malware detection and family classification in IoT devices.

关键词： IoT security Visual Explanations Multi-Teacher Knowledge Distillation Lightweight CNN

Privacy-preserving edge-assisted image retrieval and classification in IoT

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2019年第5期13卷 1136-1147页

作者： Xuan LI Jin LI Siuming YIU Chongzhi GAO Jinbo XIONG College of Mathematics and Informatics Fujian Normal University Fuzhou 350117 China Department of Computer Science The University of Hong Kong Hong Kong 999077 China Fujian Provincial Key laboratory of Network security and Cryptology Fuzhou 350117 China School of Computational Science and Education Software Guangzhou University Guangzhou 510006 China

internet of Things (IoT) has drawn much attention in recent years. However, the image data captured by IoT terminal devices are closely related to users, personal information, which are sensitive and should be protected. Though traditional privacy-preserving outsourced computing solutions such as homomorphic cryptographic primitives can support privacy-preserving computing, they consume a significant amount of computation and storage resources. Thus, it becomes a heavy burden on IoT terminal devices with limited resources. In order to reduce the resource consumption of terminal device, we propose an edge-assisted privacy-preserving outsourced computing framework for image processing, including image retrieval and classification. The edge nodes cooperate with the terminal device to protect data and support privacy-preserving computing on the semitrusted cloud server. Under this framework, edge-assisted privacy-preserving image retrieval and classification schemes are proposed in this paper. The security analysis and performance evaluation show that the proposed schemes greatly reduce the computational, communication and storage burden of IoT terminal device while ensuring image data security.

关键词： internet of Things outsourced computation privacy protection cryptographic primitive image processing

Research on the influence factors of consumer repurchase in Dutch auction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Research on the influence factors of consumer repurchase in ...

Probabilistic and Hierarchical Quantum Information Splitting Based on the Non-Maximally Entangled Cluster State

2018中国信息通信大会(CICC2018)

作者： JIANG Wei-Jin JIANG Yi-Rong CHEN Jia-Hui XU Yu-Hui WANG Yang TAN Li-Na School of Computer Science and Technology Wuhan University of Technology Key laboratory of Hunan Province for New Retail Virtual Reality Technology Hunan University of Commerce Institute of Big Data and internet Innovation Mobile E-business Collaborative Innovation Center of Hunan Province Hunan University of Commerce Tonghua Normal University

With the rapid development of e-commerce,the online shopping market becomes more and more *** to design sales models to retain consumers and make them become continuous buying is the biggest concern of most e-commerce *** study was under the situation of Dutch auction model,using a large number of real auction data in Gongtianxia’s "7 days auction" and "15 minutes auction".We use quantitative research method combining statistical analysis and panel data regression model,to study the influencing factors of consumers’ repeat *** results show that auction methods,consumers’ perceived performance and bidding structure can affect consumers *** the same time,we established random effects regression models of the rate of consumers repurchase in 7 days and 30 *** to the conclusion of the research in this article,we can provide some practical suggestions for Gongtianxia and a reference for other e-commerce.

关键词： Dutch Auction Continuous purchases Panel data Random effects model

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第10期69卷 339-349页

作者： Gang Xu Rui-Ting Shan Xiu-Bo Chen Mianxiong Dong Yu-Ling Chen School of Information Science and Technology North China University of TechnologyBeijing100144China Information security Center State Key Laboratory of Networking and Switching TechnologyBeijing University of Posts and TelecommunicationsBeijing100876China Muroran Institution of Technology Muroran050-8585Japan State Key laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China

With the emergence of classical communication security problems,quantum communication has been studied more *** this paper,a novel probabilistic hierarchical quantum information splitting protocol is designed by using a non-maximally entangled four-qubit cluster ***,the sender Alice splits and teleports an arbitrary one-qubit secret state invisibly to three remote agents Bob,Charlie,and *** agent David is in high grade,the other two agents Bob and Charlie are in low ***,the receiver in high grade needs the assistance of one agent in low grade,while the receiver in low grade needs the aid of all *** introducing an ancillary qubit,the receiver’s state can be inferred from the POVM measurement result of the ancillary ***,with the help of other agents,the receiver can recover the secret state probabilistically by performing certain unitary operation on his own *** addition,the security of the protocol under eavesdropping attacks is *** this proposed protocol,the agents need only single-qubit measurements to achieve probabilistic hierarchical quantum information splitting,which has appealing advantages in actual *** a probabilistic hierarchical quantum information splitting protocol hierarchical is expected to be more practical in multipartite quantum cryptography.

关键词： Cluster state hierarchical quantum information splitting probabilistic non-maximally entangled states

On-chain is not enough:Ensuring pre-data on the chain credibility for blockchain-based source-tracing systems

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Digital Communications and Networks 2023年第5期9卷 1053-1060页

作者： Yilei Wang Zhaojie Wang Guoyu Yang Shan Ai Xiaoyu Xiang Chang Chen Minghao Zhao School of Computer Science Qufu Normal UniversityRizhao276826China Guangxi Key laboratory of Cryptography and Information security Guilin University of Electronic TechnologyGuilin541004China Institute of Artificial Intelligence and Blockchain Guangzhou UniversityGuangzhou510006China School of Software Tsinghua UniversityTsinghua UniversityBeijing100191China

The blockchain provides a reliable and scalable method for enabling source-tracing functionality in large-scale internet of Things(IoT)*** blockchain-based source tracing applications are generally based on the hypothesis that the raw data collected by each IoT node are credible and consistent,which however may not always be the *** no mechanism ensures the reliability of the original data collected from the IoT devices,these data may be accidently screwed up or maliciously tampered with before they are uploaded *** address this issue,we propose the Multi-dimensional Certificates of Origin(MCO)method to filter out the potentially incredible data-till all the data uploaded to the chain are *** achieve this,we devise the Multidimensional Information Cross-Verification(MICV)and Multi-source Data Matching Calculation(MDMC)*** verifies whether a to-be-uploaded datum is consistent or credible,and MDMC determines which data should be discarded and which data should be kept to retain the most likely credible/untampered ones in the circumstance when data inconsistency ***-scale experiments show that our scheme ensures on the credibility of data and off the chain with an affordable overhead.

关键词： Blockchain Traceability Blockchain security

internet Web Trust System Based on Smart Contract

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

国际计算机前沿大会会议论文集 2019年第1期 309-311页

作者： Shaozhuo Li Na Wang Xuehui Du Aodi Liu He’nan Province Key laboratory of Information security Zhengzhou 450001 Henan China

The current internet web trust system is based on the traditional PKI system, to achieve the purpose of secure communication through the trusted third party. However, with the increase of network nodes, various problems appear in the centralization system of public key infrastructure (PKI). In recent years, in addition to cryptographic problems, attacks against PKI have focused on the single point of failure of certificate authority (CA). Although there are many reasons for a single point of failure, the purpose of the attack is to invalidate the CA. Thus a distributed authentication system is explored to provide a feasible solution to develop distributed PKI with the rise of the blockchain. Due to the automation and economic penalties of smart contracts, a PKI system is proposed based on smart contracts. The certificate chain was constructed in the blockchain, and a mechanism was adopted for auditing access to CA nodes in the blockchain. Experimental results show that security requirements of CA are met in this system.

关键词： Public key infrastructure Blockchain Smart contract

RAISE:A Resilient Anonymous Information Sharing Environment

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2023年第12期137卷 2743-2759页

作者： Ning Hu Ling Liu Xin Liu Kaijun Wu Yue Zhao Cyberspace Institute of Advanced Technology Guangzhou UniversityGuangzhou510006China Science and Technology on Communication security laboratory The 30th Research Institute of China Electronics Technology Group CorporationChengdu610041China College of Computer Engineering and Applied Math Changsha UniversityChangsha410022China

With the widespread application of cloud computing and network virtualization technologies,more and more enterprise applications are directly deployed in the ***,the traditional TCP/IP network transmission model does not fully consider the information security issues caused by the uncontrollable internet *** security communication solutions represented by encrypted virtual private networks(VPN)are facing multiple security *** fact,during the communication process,the user application needs to protect not only the content of the communication but also the behavior of the communication,such as the communication relationship,the communication protocol,and so *** by blockchain and software-defined networking technology,this paper proposes a resilient anonymous information sharing environment,*** RAISE system consists of user agents,a core switching network and a control cluster based on a consortium *** agents are responsible for segmenting,encrypting,and encapsulating user *** core switching network forwards user traffic according to the rules issued by the controller,and the controller dynamically calculates the forwarding rules according to the security *** from onion routing technology,RAISE adopts the controller to replace the onion routing model,which effectively overcomes the uncontrollability of *** dispersed computing model is introduced to replace the TCP/IP pipeline transmission models,which overcomes the problems of anti-tracking and traffic hijacking that cannot be solved by *** propose a blockchain control plane framework,design the desired consensus algorithmand deploy a RAISE systemconsisting of 150 nodes in an internet *** experimental results show that the use of blockchain technology can effectively improve the reliability and security of the control *** maintaining high-performance network transmission,it further provides network communicatio

关键词： Software-defined anonymous communication network blockchain network communication security