检索结果-南通市图书馆

MBB-IoT:Construction and Evaluation of IoT DDoS Traffic Dataset from a New Perspective

维普期刊数据库评论

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8期76卷 2095-2119页

作者： Yi Qing Xiangyu Liu yanhui du Department of Artificial Intelligence People’s Public Security University of ChinaBeijing100038China Department of Cybersecurity People’s Public Security University of ChinaBeijing100038China

Distributed Denial of Service(DDoS)attacks have always been a major concern in the security *** the release of malware source codes such as BASHLITE and Mirai,Internet of Things(IoT)devices have become the new source of DDoS attacks against many Internet *** there are many datasets in the field of IoT intrusion detection,such as Bot-IoT,ConstrainedApplication Protocol–Denial of Service(CoAPDoS),and LATAM-DDoS-IoT(some of the names of DDoS datasets),which mainly focus on DDoS attacks,the datasets describing new IoT DDoS attack scenarios are extremely rare,and only N-BaIoT and IoT-23 datasets used IoT devices as DDoS attackers in the construction process,while they did not use Internet applications as victims *** supplement the description of the new trend of DDoS attacks in the dataset,we built an IoT environment with mainstream DDoS attack tools such as Mirai and BASHLITE being used to infect IoT devices and implement DDoS attacks against WEB ***,data aggregated into a dataset namedMBB-IoTwere captured atWEBservers and IoT *** the MBB-IoT dataset was split into a training set and a test set,it was applied to the training and testing of the Random Forests classification *** multi-class classification metrics were good and all above 90%.Secondly,in a cross-evaluation experiment based on Support Vector Machine(SVM),Light Gradient Boosting Machine(LightGBM),and Long Short Term Memory networks(LSTM)classification algorithms,the training set and test set were derived from different datasets(MBB-IoT or IoT-23),and the test performance is better when MBB-IoT is used as the training set.

关键词： Intrusion detection IoT malware botnet DDoS dataset

Relationship between R219K polymorphism of adenosine triphosphate-binding cassette transporter 1 gene and cerebral infarction: A case-controlled analysis

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Neural Regeneration Research 2009年第5期4卷 396-400页

作者： Lifang Zhang Biao Chen yanhui du Fanyuan Kong Xianghua Fang Xiuli Feng VIP Room Affiliated Hospital of Ningxia Medical University Yinchuan 750004 Ningxia Hui Autonomous Region China Department of Neurology Beijing Xuanwu Hospital Beijing 100069 China Laboratory of Neurology Chinese National Human Genome Center Beijing 100176 China

BACKGROUND： Studies have shown that adenosine triphosphate-binding cassette transporter 1 （ABCA1） gene influences atherosclerosis. Studies have also demonstrated that cerebral infarction does not occur often in pre-menopausal women. It has been, therefore, assumed that sex plays a role in R219K polymorphism of ABCA1 gene and cerebral infarction. OBJECTIVE： To explore the relationship between lipid metabolism-correlated R219K polymorphism of ABCA1 gene, risk factors of cerebral infarction and lipid level, and to determine whether there were significant differences in gender between R219K polymorphism of ABCA1 gene and cerebral infarction. DESIGN, TIME AND SETTING： A multicentral and non-randomized, controlled study based on gene polymorphism was performed at the Chinese National Human Genome Center, and lipid concentrations were measured at Beijing Xuanwu Hospital. Patients with cerebral infarction and healthy subjects were enrolled from eight hospitals of six provinces of China between October 2002 and December 2004. PARTICIPANTS： There were 177 patients in the cerebral infarction group, including 119 males and 58 females, with a mean age of （60 -＋ 13） years, and 234 healthy subjects in the normal control group, including 79 males and 155 females, with a mean age of （58 ± 12） years. METHODS： R219K polymorphism of the ABCA1 gene was detected using polymerase chain reaction-restriction fragment length polymorphism, and blood lipid concentrations were simultaneously measured. MAIN OUTCOME MEASURES： Genotype and allele frequency of R219K polymorphic site, and blood lipid concentrations. RESULTS： RR genotype and R allele frequency of males in the cerebral infarction were significantly greater than males in the normal control group [RR genotype： x2 = 5.305, OR （95% CO, 2.326 （1.120 4.828）, P〈 0.05; R allele： x2= 4.219, OR （95% CO, 1.528 （1.019 2.292）, P〈 0.05]. In addition, RR genotype and R allele frequency of males were significantly greater than females in the cerebral

关键词： ABCA1 gene R219K polymorphism lipid cerebral infarction

在线全文

学校读者我要写书评

暂无评论

基于流量分割与填充的网站指纹防御技术

北京理工大学学报 2024年第7期44卷 750-760页

作者：黄斌杜彦辉中国人民公安大学信息网络安全学院北京100038

Tor匿名网络是一种用于保护用户通信隐私的匿名通信系统.网站指纹攻击算法通过分析用户的流量数据来破坏用户通信隐私的匿名性.为防范网站指纹攻击,研究人员提出各种网站指纹防御算法.现阶段,这些防御方法存在着防御开销高、防御性能差... 详细信息

Tor匿名网络是一种用于保护用户通信隐私的匿名通信系统.网站指纹攻击算法通过分析用户的流量数据来破坏用户通信隐私的匿名性.为防范网站指纹攻击,研究人员提出各种网站指纹防御算法.现阶段,这些防御方法存在着防御开销高、防御性能差的问题.为此提出了一种基于流量分割与填充的网站指纹防御算法.该算法由流量分割和数据单元填充这两个模块组成.流量分割模块通过使用随机数量的链路和基于数据单元间隔时间的链路切换策略,将网站流量分割并发送到不同的链路上.数据单元填充模块通过使用Break Burst和Extend Burst两个子模块,分别在传入和传出burst中注入填充数据单元,进一步混淆各个链路上的网站流量模式.在封闭世界场景下,相较于同类算法HyWF,所提算法进一步降低了最优攻击算法RF的精确率18.54%和召回率20.25%;而相较于CoMPS算法,在使用更少链路的情况下,所提算法能够进一步降低RF算法的精确率2.72%和召回率5.23%.实验结果表明,所提算法在防御性能方面优于其他同类算法,并且带来了更低的防御开销.

关键词：网络安全 Tor匿名网络网站指纹防御

Petri Net Based Research of Home Automation Communication Protocol

在线全文

学校读者我要写书评

暂无评论

Petri Net Based Research of Home Automation Communication Pr...

Broadband Constraint Based Simulated Annealing Impedance Inversion

2013年中国智能自动化学术会议

作者： Guangxuan Chen yanhui du Panke Qin Jin du Na Li People’s Public Security Univesity of China

The popularity of home automation has been increasing greatly in recent ***,during the designation of communication protocol(especially for asymmetric,parallel,distributed,uncertain or randomized protocol model) of home automation,many questions *** instance,is the protocol correct? Is every message eventually delivered and received in the right order? Can two messages with the same alternating bit value be confused? In this paper we adopt Petri net to describe and analyze the protocol of home automation. Through the analysis of dynamic properties(such as reachability,boundedness, coverability and liveness) and invariants on the base of P/Tsystem modeling and its reachable marking graph,we verified the correctness of the communication protocol and finally optimized the protocol in practice.

关键词： Communication protocol Formal method Petri net Dynamic properties

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

Broadband Constraint Based Simulated Annealing Impedance Inv...

Design and Realization of ActiveMQ Based High Performance Message Cluster

第二届国际计算科学与工程国际学术研讨会

作者： Guangxuan Chen yanhui du Panke Qin Lei Zhang People's Public Security University of China Beijing University of Posts and Telecommunications

In order to enhance the accuracy and improved the resolution of the inversion result in gas hydrate exploration, this paper proposed a new inversion method. By introducing broadband constraint based simulated annealing impedance inversion, the new method allows for a more extensive search for the optimal solution and is more efficient than exhaustive enumeration in solving global optimization problems. Compared to other inversion solutions as constraint sparse spike inversion and model based inversion, the new method not only solved the global optimization problems, but also improved the resolution of the profiles and enhanced the inversion accuracy, which is helpful to the later interpretation.

关键词： Broadband constraint Global optimization Impedance inversion Simulated annealing

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

Design and Realization of ActiveMQ Based High Performance Me...

第二届国际计算科学与工程国际学术研讨会

作者： Guangxuan Chen yanhui du Panke Qin Lei Zhang People's Public Security University of China Beijing University of Posts and Telecommunications

In order to solve the performance bottleneck problems and enhance the reliability of the message cluster, this paper proposed a new solution. By introducing ActiveMQ component and message agent, the message cluster can extend the single middleware into the message middleware environment, and thus improved the availability of the data in the shared file system and database. Meanwhile, a new algorithm and mechanism of load balancing, data synchronization and fault recovery are introduced into the message cluster that greatly enhanced the performance and reliability of the cluster.

关键词： ActiveMQ Data synchronization Fault recovery Load balancing Message cluster

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

人脸视频深度伪造检测方法综述

计算机科学与探索 2023年第1期17卷 1-26页

作者：张璐芦天亮杜彦辉中国人民公安大学信息网络安全学院北京100038 山东警察学院侦查系济南250200

深度伪造(deepfake)技术的非法应用会对社会稳定、个人名誉甚至国家安全造成恶劣影响,因此针对人脸视频的深度伪造检测成为计算机视觉领域中的难点与研究热点。目前该领域的研究建立在传统人脸识别与图像分类技术基础上,通过搭建深度学... 详细信息

深度伪造(deepfake)技术的非法应用会对社会稳定、个人名誉甚至国家安全造成恶劣影响,因此针对人脸视频的深度伪造检测成为计算机视觉领域中的难点与研究热点。目前该领域的研究建立在传统人脸识别与图像分类技术基础上,通过搭建深度学习网络判别真伪,但存在数据集质量不一、多模态特征如何有效结合、模型泛化能力较差等问题。为进一步促进深度伪造检测技术的发展,对当前各类人脸视频深度伪造算法进行了全面总结,并对已有算法进行了归类、分析、比较。首先,主要介绍人脸视频深度伪造检测数据集;其次,对近三年主要的伪造视频检测方法进行总结,以特征选择为切入点,从空间特征、时空融合特征、生物特征的角度对各项检测技术进行分类整理,并对基于水印与区块链等非主流检测方法进行介绍;然后,从特征选择、迁移学习、模型设计与训练思路等方面介绍了各类检测方法所呈现出的主流趋势;最后,对全文进行总结并对未来技术发展进行展望。

关键词：深度学习多媒体取证深度伪造视频检测人脸篡改

基于区块链的大型社交类网游敏感信息数据挖掘框架

在线全文

学校读者我要写书评

暂无评论

西安理工大学学报 2021年第3期37卷 397-402页

作者：白杰杜彦辉中国人民公安大学信息网络安全学院北京100038 温州大学国际教育学院浙江温州325035

本文针对社交类网游中敏感信息识别处理体系展开研究,提出了区块链模式下网游敏感信息即时数据挖掘框架。选取某大型社交网游聊天室数据库进行测试,采用基于Python的SKLearn库进行数据预处理,通过TensorFlow实现模型训练和验证。结果表... 详细信息

本文针对社交类网游中敏感信息识别处理体系展开研究,提出了区块链模式下网游敏感信息即时数据挖掘框架。选取某大型社交网游聊天室数据库进行测试,采用基于Python的SKLearn库进行数据预处理,通过TensorFlow实现模型训练和验证。结果表明:针对网游语境中的短文本识别,TextCNN的准确率高于朴素贝叶斯、CNN两种模型5%以上,因此在模型数据层中引入TextCNN模型能够满足大型网游中敏感信息识别高效、精准的要求。结论证明,区块链模式下的网游敏感信息挖掘框架具有联盟链的层级管理优势、分布式账本对信息传播全程留痕的特性,并能通过智能合约和共识机制提升合约执行力。

关键词：网络敏感信息社交类网游区块链模型深度学习

在线全文

学校读者我要写书评

暂无评论

基于关键节点识别算法的重点人分析

北京航空航天大学学报 2024年第7期50卷 2074-2082页

作者：韩奕孙百兵王军国杜彦辉中国人民公安大学信息网络安全学院北京100038 公安部第一研究所北京100049 南京森林警察学院南京210023

关键节点识别算法是社交网络研究领域的重要分支,但现有研究成果大多对数据的多样性、完整性、可用性等依赖程度高,导致在公安机关重点人分析场景中适用性较低。因此,对静态网络拓扑结构进行量化表示,同时结合局部最优算法和全局最优算... 详细信息

关键节点识别算法是社交网络研究领域的重要分支,但现有研究成果大多对数据的多样性、完整性、可用性等依赖程度高,导致在公安机关重点人分析场景中适用性较低。因此,对静态网络拓扑结构进行量化表示,同时结合局部最优算法和全局最优算法重新定义关系度指标,再基于该指标构建特征矩阵,提出适用于公安部门重点人分析的特征向量中心性(REC)算法。依托公开数据集、2部影视剧人物关系网络、境外社交平台账号网络和国内某诈骗团伙5个数据集,从网络传播能力、抗打击弹性和重点人分析结果一致性3个维度证实所提算法的有效性,相较于其他传统挖掘算法能准确识别社交网络重要节点,具有较为广泛的应用场景。

关键词：关键节点社交网络关系度特征矩阵肯德尔