检索结果-南通市图书馆

A New Network Coding Mechanism Balancing Coding Opportunities, Energy and QoS in WSNs

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

China Communications 2014年第6期11卷 108-118页

作者： zheng kangfeng WANG Xiujuan ZHA Xuan XIAO Huan School of Computer Science Beijing University of Posts and Telecommunications School of Computer Science Beijing University of Technology

A new Network Coding mechanism in WSNs(Wireless Sensor Networks), which is named COEQ and aims at balancing coding opportunities, energy and QoS, is proposed and analyzed. Implemented on the basis of traditional AODV protocol, COEQ evaluates several metrics of paths comprehensively with TOPSIS method including minimum remaining energy, coding opportunities, QoS and so on, so as to select the optimal transmitting route. Experiments on NS[2] show that COEQ can improve throughput and save energy when the transmitting rate is low.

关键词： network coding wireless sensor network QoS TOPSIS

Semi-GSGCN: Social Robot Detection Research with Graph Neural Network

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

Computers, Materials & Continua 2020年第10期65卷 617-638页

作者： Xiujuan Wang Qianqian zheng kangfeng zheng Yi Sui Jiayue Zhang Information Technology Institute Beijing University of TechnologyBeijing100124China School of Cyberspace Security Beijing University of Posts and TelecommunicationsBeijing100876China

Malicious social robots are the disseminators of malicious information on social networks,which seriously affect information security and network *** and reliable classification of social robots is crucial for detecting information manipulation in social *** classification based on manual feature extraction has been widely used in social robot ***,these methods not only involve the privacy of users but also ignore hidden feature information,especially the graph feature,and the label utilization rate of semi-supervised algorithms is *** at the problems of shallow feature extraction and low label utilization rate in existing social network robot detection methods,in this paper a robot detection scheme based on weighted network topology is proposed,which introduces an improved network representation learning algorithm to extract the local structure features of the network,and combined with the graph convolution network(GCN)algorithm based on the graph filter,to obtain the global structure features of the *** end-to-end semi-supervised combination model(Semi-GSGCN)is established to detect malicious social *** on a social network dataset(cresci-rtbust-2019)show that the proposed method has high versatility and effectiveness in detecting social *** addition,this method has a stronger insight into robots in social networks than other methods.

关键词： Social networks social robot detection network representation learning graph convolution network

C2Net-YOLOv5: A Bidirectional Res2Net-Based Traffic Sign Detection Algorithm

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第11期77卷 1949-1965页

作者： Xiujuan Wang Yiqi Tian kangfeng zheng Chutong Liu Faculty of Information Technology Beijing University of TechnologyBeijing100124China School of Cyberspace Security Beijing University of Posts and TelecommunicationsBeijing100048China Fan Gongxiu Honors College Beijing University of TechnologyBeijing100124China

Rapid advancement of intelligent transportation systems(ITS)and autonomous driving(AD)have shown the importance of accurate and efficient detection of traffic ***,certain drawbacks,such as balancing accuracy and real-time performance,hinder the deployment of traffic sign detection algorithms in ITS and AD *** this study,a novel traffic sign detection algorithm was proposed based on the bidirectional Res2Net architecture to achieve an improved balance between accuracy and *** enhanced backbone network module,called C2Net,which uses an upgraded bidirectional Res2Net,was introduced to mitigate information loss in the feature extraction process and to achieve information ***,a squeeze-and-excitation attention mechanism was incorporated within the channel attention of the architecture to perform channel-level feature correction on the input feature map,which effectively retains valuable features while removing non-essential features.A series of ablation experiments were conducted to validate the efficacy of the proposed *** performance was evaluated using two distinct datasets:the Tsinghua-Tencent 100K and the CSUST Chinese traffic sign detection benchmark *** the TT100K dataset,the method achieves precision,recall,and Map0.5 scores of 83.3%,79.3%,and 84.2%,***,on the CCTSDB 2021 dataset,the method achieves precision,recall,and Map0.5 scores of 91.49%,73.79%,and 81.03%,*** results revealed that the proposed method had superior performance compared to conventional models,which includes the faster region-based convolutional neural network,single shot multibox detector,and you only look once version 5.

关键词： Target detection traffic sign detection autonomous driving YOLOv5

Smartphone Malware Detection Model Based on Artificial Immune System

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Communications 2014年第A1期11卷 86-92页

作者： WU Bin LU Tianliang zheng kangfeng ZHANG Dongmei LIN Xing InformationSecurityLaboratory NationalDisasterRecoveryTechnologyEngineeringLaboratoryBeijingUniversityofPostsandTelecommunicationsBeijing100876P.R.China People'sPublicSecurityUniversityofChina Beijing100038P.R.China

In order to solve the problem that me traditional signature-based detection technology cannot effectively detect unknown malware, we propose in this study a smartphone malware detection model （SP-MDM） based on artificial immune system, in which static malware analysis and dynamic malware analysis techniques are combined, and antigens are generated by encoding the characteristics extracted from the malware. Based on negative selection algorithm, the mature detectors are generated. By introducing clonal selection algorithm, the detectors with higher affinity are selected to undergo a proliferation and somatic hyper-mutation process, so that more excellent detector offspring can be generated. Experimental result shows that the detection model has a higher detection rate for unknown smartphone malware, and better detection performance can be achieved by increasing the clone generation.

关键词： artificial immune system smartphonemalware detection negative selection clonalselection

Strategy Selection for Moving Target Defense in Incomplete Information Game

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2020年第2期62卷 763-786页

作者： Huan Zhang kangfeng zheng Xiujuan Wang Shoushan Luo Bin Wu School of CyberSpace Security Beijing University of Posts and TelecommunicationsBeijing100088China College of Computer Sciences Beijing University of TechnologyBeijing100124China

As a core component of the network,web applications have become one of the preferred targets for attackers because the static configuration of web applications simplifies the exploitation of vulnerabilities by *** the moving target defense(MTD)has been proposed to increase the attack difficulty for the attackers,there is no solo approach can cope with different attacks;in addition,it is impossible to implement all these approaches simultaneously due to the resource ***,the selection of an optimal defense strategy based on MTD has become the focus of *** general,the confrontation of two players in the security domain is viewed as a stochastic game,and the reward matrices are known to both ***,in a real security confrontation,this scenario represents an incomplete information *** player can only observe the actions performed by the opponent,and the observed actions are not completely *** accurately describe the attacker’s reward function to reach the Nash equilibrium,this work simulated and updated the strategy selection distribution of the attacker by observing and investigating the strategy selection history of the ***,the possible rewards of the attacker in each confrontation via the observation matrix were *** this basis,the Nash-Q learning algorithm with reward quantification was proposed to select the optimal ***,the performances of the Minimax-Q learning algorithm and Naive-Q learning algorithm were compared and analyzed in the MTD ***,the experimental results showed that the strategy selection algorithm can enable defenders to select a more reasonable defensive strategy and achieve the maximum possible reward.

关键词： Moving target defense Nash-Q learning algorithm optimal strategy selection incomplete information game web service

Efficient User Identity Linkage Based on Aligned Multimodal Features and Temporal Correlation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第10期81卷 251-270页

作者： Jiaqi Gao kangfeng zheng Xiujuan Wang Chunhua Wu Bin Wu School of Cyberspace Security Beijing University of Posts and TelecommunicationsBeijing100876China Faculty of Information Technology Beijing University of TechnologyBeijing100124China

User identity linkage(UIL)refers to identifying user accounts belonging to the same identity across different social media *** of the current research is based on text analysis,which fails to fully explore the rich image resources generated by users,and the existing attempts touch on the multimodal domain,but still face the challenge of semantic differences between text and *** this,we investigate the UIL task across different social media platforms based on multimodal user-generated contents(UGCs).We innovatively introduce the efficient user identity linkage via aligned multi-modal features and temporal correlation(EUIL)*** method first generates captions for user-posted images with the BLIP model,alleviating the problem of missing textual ***,we extract aligned text and image features with the CLIP model,which closely aligns the two modalities and significantly reduces the semantic ***,we construct a set of adapter modules to integrate the multimodal ***,we design a temporal weight assignment mechanism to incorporate the temporal dimension of user *** evaluate the proposed scheme on the real-world social dataset TWIN,and the results show that our method reaches 86.39%accuracy,which demonstrates the excellence in handling multimodal data,and provides strong algorithmic support for UIL.

关键词： User identity linkage multimodal models attention mechanism temporal correlation

Social Engineering Attack-Defense Strategies Based on Reinforcement Learning

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 Systems Science & Engineering 2023年第11期47卷 2153-2170页

作者： Rundong Yang kangfeng zheng Xiujuan Wang Bin Wu Chunhua Wu School of Cyberspace Security Beijing University of Posts and TelecommunicationsBeijing100876China School of Computer Science Beijing University of TechnologyBeijing100124China

Social engineering attacks are considered one of the most hazardous cyberattacks in cybersecurity,as human vulnerabilities are often the weakest link in the entire *** vulnerabilities are becoming increasingly susceptible to network security *** the social engineering attack defense problem has been the focus of many ***,two main challenges hinder its successful ***,the vulnerabilities in social engineering attacks are unique due to multistage attacks,leading to incorrect social engineering defense ***,social engineering attacks are real-time,and the defense strategy algorithms based on gaming or reinforcement learning are too complex to make rapid *** paper proposes a multiattribute quantitative incentive method based on human vulnerability and an improved Q-learning(IQL)reinforcement learning method on human vulnerability *** proposed algorithm aims to address the two main challenges in social engineering attack defense by using a multiattribute incentive method based on human vulnerability to determine the optimal defense ***,the IQL reinforcement learning method facilitates rapid decision-making during real-time *** experimental results demonstrate that the proposed algorithm outperforms the traditional Qlearning(QL)and deep Q-network(DQN)approaches in terms of time efficiency,taking 9.1%and 19.4%less time,***,the proposed algorithm effectively addresses the non-uniformity of vulnerabilities in social engineering attacks and provides a reliable defense strategy based on human vulnerability *** study contributes to advancing social engineering attack defense by introducing an effective and efficient method for addressing the vulnerabilities of human factors in the cybersecurity domain.

关键词： Social engineering game theory reinforcement learning Q-learning

An Efficient Algorithm for Indoor Positioning in WLAN Environments using KNN Algorithm and Pass-Loss Model

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

An Efficient Algorithm for Indoor Positioning in WLAN Enviro...

2011年全国通信安全学术会议

作者： Liangzi Ding,kangfeng zheng Information Security Center,Beijing University of Posts and Telecommunications Beijing 100876,China

＜正＞A new approach has been presented to increase the location estimation accuracy in WLAN *** Location fingerprint method base on KNN algorithm,optimal parameter has not been theoretically *** studies have shown that value of k in KNN algorithm have a great impact on the positioning accuracy and should comprehensively consider the cumulative probability,the average location error distance,the complexity of the algorithm and some other *** novel technology we propose provides a practical method to select the value of k *** first uses triangulation location method based on Pass - Loss model to calculate the area where the typical measured point may exist,and then uses the traditional KNN algorithm to select k closest vectors from the regional location fingerprint database which are in the triangulation location intersection district,finally calculate their estimated *** experimental results show that the new method improves the original KNN algorithm and can achieve a great positioning accuracy.

关键词： location fingerprint KNN algorithm Pass - Loss Triangulation location

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

网络空间安全中的人格研究综述

电子与信息学报 2020年第12期42卷 2827-2840页

作者：吴桐郑康锋伍淳华王秀娟郑赫慈北京邮电大学网络空间安全学院北京100876 北京工业大学信息学部北京100124

网络空间是所有信息系统的集合,是人类赖以生存的信息环境。网络空间安全已经从物理域、信息域安全扩展到以人为中心的认知域和社会域安全,对人的安全研究已经成为了网络空间安全的必然趋势。人是复杂多变的综合体,而人格作为人的稳定... 详细信息

网络空间是所有信息系统的集合,是人类赖以生存的信息环境。网络空间安全已经从物理域、信息域安全扩展到以人为中心的认知域和社会域安全,对人的安全研究已经成为了网络空间安全的必然趋势。人是复杂多变的综合体,而人格作为人的稳定的心理特征,成为了人的安全相关研究的切入点。该文梳理当前网络空间安全中的人格研究,介绍了网络空间安全和人格的基本概念,提出了网络空间安全中人格的研究框架,涵盖理论研究、技术研究和技术应用3个层次;其中技术研究主要包括人格测量、人格的安全脆弱性和针对人的安全防护3部分;详细探讨了当前人格安全研究现状和存在的问题,最后讨论了未来的研究方向和发展趋势。

关键词：人格网络空间安全人格测量人格脆弱性安全防护