基于行为测量的P2P系统优化研究
|
摘要
随着主机性能的不断提升和网络带宽的快速增长，互联网涌现出一系列新的分布式应用成果。对等网络(Peer-to-Peer，简称P2P)无疑是21世纪初发展最为迅猛、使用最为广泛的互联网应用之一。不同于传统Client/Server模型，P2P秉承互联网发展初期的设计理念，充分利用位于网络边缘的大量计算、存储和带宽等资源，形成规模巨大、扩展性良好的覆盖网络，并为其上的用户提供优质的服务。P2P高效、经济、高扩展性的优点吸引了众多企业和用户的目光，也成为学术界关注的焦点。然而，不当的设计和必要安全机制的缺乏，造成了P2P网络与信息安全事件频发，制约了P2P网络应用的进一步推广。此外，由于庞大的网络规模使得人们缺乏对P2P网络的深刻理解和全面认识，难以对P2P系统进行直接的评价和改进。本文的研究着重于通过网络测量的方法刻画P2P网络的行为并优化P2P系统。
本文首先系统地介绍了P2P网络的概念、特点、结构以及分类，并详细总结了当前P2P网络测量的研究现状和面临的主要安全问题。然后本文以行为研究为脉络，以典型的P2P文件共享系统为目标，分别从宏观系统行为、外部流量行为、内部路由行为和主要攻击行为四个角度研究当前主流P2P网络，并针对性地提出了改进P2P系统的方法和建议。
随着P2P网络及其技术的不断发展，网络整体行为逐渐发生着变化，现有测量方法已无法适应当前系统，测量方法的效率和完整性均有待提高。由于BitTorrent系统是一种典型的混杂网络，构成复杂，组件分散在多个网络，其研究能够为其他P2P系统测量工作提供指导。为此，本文提出了一个高效的BitTorrent测量系统，涵盖了种子采集、共享节点探测、文件片断收集、被动收集等多项功能。在此基础上，本文对BitTorrent系统进行了长期观测，实际测量了其内容、核心组件、节点和文件片断等系统行为特性，并指出其潜在的性能瓶颈和影响因素。此外，本文改进了节点到达模型，增加日周期性的描述，并考察了不同流行度资源间的特性差异。
宏观系统行为体现的是所有参与节点的群体行为特性，个体行为特征需要更加细微的观察与测量。单个节点的外部行为研究则为了解内在运行机制提供了最为直接的途径。为了考察P2P节点的外部行为，本文立足于研究P2P网络的一种典型流量—DHT(Distributed Hash Tables)网络流量，发现其外在的行为模式。为此，本文提出了基于复合行为的DHT流量识别方法，刻画了DHT网络异于传统网络的流量行为模式，能够帮助间接识别P2P主机。该方法通过分析DHT内在固有机制，充分利用DHT节点的路由特性，提取出多种行为模式(自举行为、路由行为、多样行为和短会话行为)。实验表明，该方法能够较好地分辨P2P主机。
外部行为是内部机制的体现，内部机制的研究与改进能够直接优化P2P网络性能。为此，本文研究了DHT路由表性能，并在此基础上通过优化路由表结构以及改进路由表更新算法提高其性能。为了评估路由表性能，本文研究了影响路由表规模、增长幅度和扰动程度的主要因素，并考察了核心运行参数(自查询间隔、消息超时和查询并行度)对路由表性能的影响。在此基础上，本文分析了路由表K桶结构以及更新算法，提出了容量可变的K桶和基于K桶分散度的更新算法。实验结果表明改进后的客户端路由性能更好。
攻击行为的研究有利于提高P2P系统的安全性，同时也有效地保证了其上用户的共享效率。为了加强P2P安全防护，本文研究了BitTorrent系统常见的攻击行为，剖析了典型攻击的攻击原理。在此基础上，本文进一步量化了Leechers攻击行为并讨论了影响Leechers攻击的主要因素，并指出了通过限制恶意节点资源或提高正常节点资源的方法能够有效地抵御此类攻击的影响。通过广域网实验看出，当前BitTorrent系统容易受到攻击行为的影响，也验证了防护策略的可行性。
总体而言，本文对P2P网络行为进行系统的研究，深入地分析了影响P2P网络性能的因素及安全威胁，提出的技术和方法能够有效提高P2P网络的性能和安全性，并对未来P2P网络研究的开展具有指导意义。
With continuous improvement of PC performance and rapid development ofnetwork bandwidth, lots of new distributed applications are emerging in the Internet.Peer-to-Peer network (P2P) is undoubtedly one of the most successful andwidelyusing applications in early21st century. Different from traditionalclient/server model, P2P adheres to design philosophy in early period of Internetdevelopment, takes full advantage of mass resources (computation, storage,bandwidth, etc) on the edge of network, forms a huge and scalable overlay networkand provides good services to the users. The convenient, economical and elasticresources in P2P are attracting more and more attentions from the enterprises andusers. It is becoming the focus of the academia. However, similar to the Internet,the vast scale of P2P network poses an obstacle to the direct evaluation andimprovement itself without profound understanding. Inappropriate design andincomplete security mechanisms not only result in the loss of performance, but giveattackers the opportunity to exploit P2P for attacking, which are confining itspopularization and development severely. This dissertation is dedicated to profilingthe behaviors of P2P network by means of network measurement in order tooptimize P2P system.
Firstly, this dissertation systematically introduces the concept, characteristic,architecture and classification of P2P network, and presents a detail survey ofresearch on P2P measurement and security issues. Then, current popular P2Pnetworks are studied and measured in the following views separately: systematicbehavior, external behavior, internal behavior and attack behavior, and severalimprovements and suggestions are proposed specifically.
Because the overall behaviors of P2P network are changing gradually with thedevelopment of P2P technologies, existing measurement methods cannot carry outall aspects of P2P systems, whose efficiency and integrity need to be promoted.Since BitTorrent is a kind of hybrid network with complex components crossingmultiple networks, the study on it can serve an effective guide for the measurementof other P2P systems. This dissertation proposes an efficient measurement system for BitTorrent, including torrents collection, peers probing, pieces gathering andpassive monitoring. Then based on the system, a complete and representativemeasurement is performed for a long time to profile the characteristics of content,core components, peers and pieces, and point out potential performance bottleneckor influencing factors. Furthermore, an improved model is also proposed to depictthe daily pattern of peer arrival rate which is not well modeled before, and tworesources with different popularity are also contrasted.
The macroscopic behaviors mainly stand for group characteristics of allparticipants, but individual characteristics need more elaborate measurement andobservation. The study on external behaviors of single peer provides a direct way toshed light on the internal working mechanisms. In order to investigate the externalbehaviors, this dissertation works on a typical kind of traffic in P2P networks—Distributed Hash Table. DHT traffic identification based on compound behaviors isproposed to describe the distinctive traffic pattern and can identify P2P hostsindirectly. It analyzes the DHT intrinsic mechanisms, makes good use of the routingrole and discovers several behavior patterns, such as bootstrap behavior, routingbehavior, diverse behavior and short-session behavior. The experimental resultsshow this method can distinguish P2P hosts from others.
The external behaviors reflect the characteristics in the way of black box whenP2P hosts connect to others, which are the embodiment of internal implement, sothe measurement of internal behaviors can guide system design and improvementbetter. Therefore, this dissertation focuses on the performance enhancement of DHTrouting by optimizing the structure of routing tables and improving the updatingalgorithm. To evaluate the performance, several characteristics of local routingtable are studied intensively, including the size of routing table, growth and theratio of churn, and moreover the effect of different key running parameters(find_self action interval, message timeout and parallel degree) are discussed. K-bucket with mutable size and updating algorithm based on dispersity of K-bucketare proposed subsequently. The results of corresponding experiments show theimproved routing table is better than the original one.
The study on attacks is an important aspect of P2P behaviors research, because attacks have a serious impact on sharing efficiency in P2P network. For this reason,this dissertation presents a study on the common attacks in BitTorrent, and analyzesthe principles of different attacks. On this condition, this dissertation analyzes theleechers attack theoretically, and discusses the extra factors to affect the result offake-block attack and points out the design of security mechanism to counteragainst these attacks. The experiments on WAN show that BitTorrent system isvulnerable to leechers and fake-block attacks, which also proves the effectivenessof the proposed defense strategies.
Overall, this dissertation systematically researches the behaviors of P2Pnetwork, and analyzes the factors and security threats impairing the performance ofP2P network. The proposed methods and technologies can effectively improve theperformance and enhance the security of P2P network, which is significant for thefuture research on P2P network.
本文首先系统地介绍了P2P网络的概念、特点、结构以及分类，并详细总结了当前P2P网络测量的研究现状和面临的主要安全问题。然后本文以行为研究为脉络，以典型的P2P文件共享系统为目标，分别从宏观系统行为、外部流量行为、内部路由行为和主要攻击行为四个角度研究当前主流P2P网络，并针对性地提出了改进P2P系统的方法和建议。
随着P2P网络及其技术的不断发展，网络整体行为逐渐发生着变化，现有测量方法已无法适应当前系统，测量方法的效率和完整性均有待提高。由于BitTorrent系统是一种典型的混杂网络，构成复杂，组件分散在多个网络，其研究能够为其他P2P系统测量工作提供指导。为此，本文提出了一个高效的BitTorrent测量系统，涵盖了种子采集、共享节点探测、文件片断收集、被动收集等多项功能。在此基础上，本文对BitTorrent系统进行了长期观测，实际测量了其内容、核心组件、节点和文件片断等系统行为特性，并指出其潜在的性能瓶颈和影响因素。此外，本文改进了节点到达模型，增加日周期性的描述，并考察了不同流行度资源间的特性差异。
宏观系统行为体现的是所有参与节点的群体行为特性，个体行为特征需要更加细微的观察与测量。单个节点的外部行为研究则为了解内在运行机制提供了最为直接的途径。为了考察P2P节点的外部行为，本文立足于研究P2P网络的一种典型流量—DHT(Distributed Hash Tables)网络流量，发现其外在的行为模式。为此，本文提出了基于复合行为的DHT流量识别方法，刻画了DHT网络异于传统网络的流量行为模式，能够帮助间接识别P2P主机。该方法通过分析DHT内在固有机制，充分利用DHT节点的路由特性，提取出多种行为模式(自举行为、路由行为、多样行为和短会话行为)。实验表明，该方法能够较好地分辨P2P主机。
外部行为是内部机制的体现，内部机制的研究与改进能够直接优化P2P网络性能。为此，本文研究了DHT路由表性能，并在此基础上通过优化路由表结构以及改进路由表更新算法提高其性能。为了评估路由表性能，本文研究了影响路由表规模、增长幅度和扰动程度的主要因素，并考察了核心运行参数(自查询间隔、消息超时和查询并行度)对路由表性能的影响。在此基础上，本文分析了路由表K桶结构以及更新算法，提出了容量可变的K桶和基于K桶分散度的更新算法。实验结果表明改进后的客户端路由性能更好。
攻击行为的研究有利于提高P2P系统的安全性，同时也有效地保证了其上用户的共享效率。为了加强P2P安全防护，本文研究了BitTorrent系统常见的攻击行为，剖析了典型攻击的攻击原理。在此基础上，本文进一步量化了Leechers攻击行为并讨论了影响Leechers攻击的主要因素，并指出了通过限制恶意节点资源或提高正常节点资源的方法能够有效地抵御此类攻击的影响。通过广域网实验看出，当前BitTorrent系统容易受到攻击行为的影响，也验证了防护策略的可行性。
总体而言，本文对P2P网络行为进行系统的研究，深入地分析了影响P2P网络性能的因素及安全威胁，提出的技术和方法能够有效提高P2P网络的性能和安全性，并对未来P2P网络研究的开展具有指导意义。
With continuous improvement of PC performance and rapid development ofnetwork bandwidth, lots of new distributed applications are emerging in the Internet.Peer-to-Peer network (P2P) is undoubtedly one of the most successful andwidelyusing applications in early21st century. Different from traditionalclient/server model, P2P adheres to design philosophy in early period of Internetdevelopment, takes full advantage of mass resources (computation, storage,bandwidth, etc) on the edge of network, forms a huge and scalable overlay networkand provides good services to the users. The convenient, economical and elasticresources in P2P are attracting more and more attentions from the enterprises andusers. It is becoming the focus of the academia. However, similar to the Internet,the vast scale of P2P network poses an obstacle to the direct evaluation andimprovement itself without profound understanding. Inappropriate design andincomplete security mechanisms not only result in the loss of performance, but giveattackers the opportunity to exploit P2P for attacking, which are confining itspopularization and development severely. This dissertation is dedicated to profilingthe behaviors of P2P network by means of network measurement in order tooptimize P2P system.
Firstly, this dissertation systematically introduces the concept, characteristic,architecture and classification of P2P network, and presents a detail survey ofresearch on P2P measurement and security issues. Then, current popular P2Pnetworks are studied and measured in the following views separately: systematicbehavior, external behavior, internal behavior and attack behavior, and severalimprovements and suggestions are proposed specifically.
Because the overall behaviors of P2P network are changing gradually with thedevelopment of P2P technologies, existing measurement methods cannot carry outall aspects of P2P systems, whose efficiency and integrity need to be promoted.Since BitTorrent is a kind of hybrid network with complex components crossingmultiple networks, the study on it can serve an effective guide for the measurementof other P2P systems. This dissertation proposes an efficient measurement system for BitTorrent, including torrents collection, peers probing, pieces gathering andpassive monitoring. Then based on the system, a complete and representativemeasurement is performed for a long time to profile the characteristics of content,core components, peers and pieces, and point out potential performance bottleneckor influencing factors. Furthermore, an improved model is also proposed to depictthe daily pattern of peer arrival rate which is not well modeled before, and tworesources with different popularity are also contrasted.
The macroscopic behaviors mainly stand for group characteristics of allparticipants, but individual characteristics need more elaborate measurement andobservation. The study on external behaviors of single peer provides a direct way toshed light on the internal working mechanisms. In order to investigate the externalbehaviors, this dissertation works on a typical kind of traffic in P2P networks—Distributed Hash Table. DHT traffic identification based on compound behaviors isproposed to describe the distinctive traffic pattern and can identify P2P hostsindirectly. It analyzes the DHT intrinsic mechanisms, makes good use of the routingrole and discovers several behavior patterns, such as bootstrap behavior, routingbehavior, diverse behavior and short-session behavior. The experimental resultsshow this method can distinguish P2P hosts from others.
The external behaviors reflect the characteristics in the way of black box whenP2P hosts connect to others, which are the embodiment of internal implement, sothe measurement of internal behaviors can guide system design and improvementbetter. Therefore, this dissertation focuses on the performance enhancement of DHTrouting by optimizing the structure of routing tables and improving the updatingalgorithm. To evaluate the performance, several characteristics of local routingtable are studied intensively, including the size of routing table, growth and theratio of churn, and moreover the effect of different key running parameters(find_self action interval, message timeout and parallel degree) are discussed. K-bucket with mutable size and updating algorithm based on dispersity of K-bucketare proposed subsequently. The results of corresponding experiments show theimproved routing table is better than the original one.
The study on attacks is an important aspect of P2P behaviors research, because attacks have a serious impact on sharing efficiency in P2P network. For this reason,this dissertation presents a study on the common attacks in BitTorrent, and analyzesthe principles of different attacks. On this condition, this dissertation analyzes theleechers attack theoretically, and discusses the extra factors to affect the result offake-block attack and points out the design of security mechanism to counteragainst these attacks. The experiments on WAN show that BitTorrent system isvulnerable to leechers and fake-block attacks, which also proves the effectivenessof the proposed defense strategies.
Overall, this dissertation systematically researches the behaviors of P2Pnetwork, and analyzes the factors and security threats impairing the performance ofP2P network. The proposed methods and technologies can effectively improve theperformance and enhance the security of P2P network, which is significant for thefuture research on P2P network.
引文
[1] Hauben M, Hauben R. Behind the Net: The Untold Story of the Arpanet andComputer Science[J]. First Monday,1998,3（8）.
[2] Berners-Lee T J, et al. The World Wide Web[J]. Communications of the ACM,1994,37（8）：76-82.
[3] ANSI T1.413-1998. Network and Customer Installation Interfaces–Asymmetric Digital Subscriber Line (ADSL) Metallic Interface, AmericanNational Standards Institute1998.
[4] Cisco Company. Cisco Visual Networking Index: Forecast and Methodology,2009-2014[EB/OL][2011-04-25]. http://www.cisco.com/en/US/solutions/collateral/ns341/ns525/ns537/ns705/ns827/white_paper_c11481360_ns827_Networking_Solutions_White_Paper.html
[5]中国互联网络信息中心.第26次中国互联网络发展状况统计报告[EB/OL][2011-03-11]. http://www.cnnic.net.cn/xzzx/tjbgxz/201010/t20101020_16004.html
[6] BitTorrent[EB/OL][2010-11-11]. http://bitconjurer.org/BitTorrent.
[7] eMule[EB/OL][2010-12-5]. http://www.emule-project.net.
[8] Chen H, Yang M, Han J, et al. Maze: a Social Peer-to-peer Network[C].Proceedings of the IEEE International Conference on E-CommerceTechnology for Dynamic E-Business, Beijing: IEEE Press,2004：290-293.
[9] Kubiatowicz J, Bindel D, Chen Y, et al. OceanStore: An Architecture forGlobal-Scale Persistent Storage[C]. Proceedings of the9th InternationalConference on Architectural Support for Programming Languages andOperating Systems, New York, NY, USA: ACM,2000,35（11）：190-201.
[10] Zheng W, Hu J, Li M. Granary: Architecture of Object Oriented InternetStorage Service[C]. Proceedings of the IEEE International Conference on E-Commerce Technology for Dynamic E-Business, Beijing: IEEE Press,2004：294-297.
[11] Huang Y, Fu T Z J, Chiu D, et al. Challenges, design and analysis of a large-scale p2p-vod system[C]. Proceedings of the ACM SIGCOMM2008conference on Data communication, New York, NY, USA: ACM,2008：375-388.
[12] Liao X, Jin H, Liu Y, et al. AnySee: Peer-to-Peer Live Streaming[C].Proceedings of the25th IEEE International Conference on ComputerCommunications, Barcelona: IEEE Press,2006：1-10.
[13] Skype[EB/OL][2011-03-03]. http://www.skype.com.
[14] SETI@home[EB/OL][2011-03-03]. http://setiathome.berkeley.edu.
[15] Napster[EB/OL][2011-03-03]. http://www.napster.com
[16] Gnutella[EB/OL][2011-03-03]. http://rfc-gnutella.sourceforge.net.
[17] KaZaA[EB/OL][2011-03-03]. http://www.kazaa.com.
[18] Maymounkov P, Mazières D. Kademlia: A Peer-to-Peer Information SystemBased on the XOR Metric[C]. Proceedings of the First International Workshopon Peer-to-Peer System, Cambridge, MA, USA: Springer-Verlag,2002：53-65.
[19] Xie H, Yang Y R, Krishnamurthy A, et al. P4P: provider portal forapplications[C]. Proceedings of the ACM SIGCOMM2008conference onData communication, New York, NY, USA: ACM,2008：351-362.
[20] Tuotu[EB/OL][2011-03-04]. http://www.tuotu.com.
[21]王继龙，吴建平. Internet行为学[EB/OL][2011-03-16]. http://wenku.baidu.com/view/31ceb01252d380eb62946da0.html
[22]程光，龚俭，丁伟.网络测量及行为学研究综述[J].计算机工程与应用，2004，40（27）：1-8.
[23] Paxson V E. Measurements and Analysisof End-to-End Internet Dynamics[D].Berkeley: University of California,1997.
[24] Mahdavi J, Paxson V. IPPM Metrics for Measuring Connectivity[R]. RFC2678, Sep1999.
[25] Almes G, Kalidindi S, Zekauskas M. A One-way Delay Metric for IPPM[R].RFC2679, Sep1999.
[26] Almes G, Kalidindi S, Zekauskas M. A One-way Packet Loss Metric forIPPM[R]. RFC2680, Sep1999.
[27] Almes G, Kalidindi S, Zekauskas M. A Round-trip Delay Metric for IPPM[R].RFC2681, Sep1999.
[28] Leland W E, Taqqu M S, W. Willinger, et al. On the self-similar nature ofethernet traffic[J]. IEEE/ACM Transaction on Networking,1994,2（1）：1-15.
[29] Zhang Y, Paxson V, Shenker S. The stationarity of internet path properties:Routing, loss, and throughput[R]. Technical report, ACIRI,2000.
[30] Paxson V. End-to-end routing behavior in the internet[J]. ACM SIGCOMMComputer Communication Review, ACM, New York, NY, USA,2006：41-56.
[31] Shaikh A, Varma A, Kalampoukas L, et al. Routing stability in congestednetworks: experimentation and analysis[C]. Proceedings of the conference onApplications, Technologies, Architectures, and Protocols for ComputerCommunication, New York, NY, USA: ACM,2000：163-174.
[32]裴昌幸，等,现代通信系统与网络测量[M].北京：人民邮电出版社，2008：70-71.
[33] Horváth, Telek M. A Markovian Point Process Exhibiting MultifractalBehavior and its Application to Traffic Modeling[C]. Proceedings of4thInternational Conference on Matrix-analytic Methods in Stochastic Models,Adelaide, Australia,2002：1-12.
[34] NS-2[EB/OL][2010-12-01]. http://www.isi.edu/nsnam/ns/.
[35] Oram A. Peer-to-Peer Harnessing the power of disruptive technologies[M].California: O'Reilly Media,2001：1-20
[36] Lua E K, Crowcroft J, Pias M, et al. A survey and comparison of peer-to-peeroverlay network schemes[J]. Journal of IEEE Communications Survey andTutorial,2005,7（2）：72-93.
[37]郑纬民,胡进锋,代亚非，等.对等计算研究概论[M].中国计算机学会通讯,2005：38-51.
[38]张宇翔,杨冬,张宏科. P2P网络中Churn问题研究[J].软件学报,2009,20（5）：1362-1376.
[39] eDonkey2000[EB/OL][2011-01-12]. http://emulefans.com.
[40] Borland J, RIAA threat may be slowing file swapping[EB/OL][2010-10-15].http://news.cnet.com/2100-1027-1025684.html.
[41] Lv Q, Cao P, Cohen E, et al. Search and replication in unstructured peer-to-peer networks[C]. Proceedings of the16th international conference onSupercomputing, New York, NY, USA: ACM,2002：84-95.
[42] Gkantsidis C, Mihail M, Saberi A. Random walks in peer-to-peer networks:algorithms and evaluation[J]. Performance Evaluation, HongKong, CN,2006,63（3）：241-263.
[43] Stoica, Morris R, Karger D, et al. Chord: A Scalable Peer-to-peer LookupService for Internet Applications[C]. Proceedings of the2001conference onApplications, technologies, architectures, and protocols for computercommunications, New York, NY, USA: ACM,2001：149-160.
[44] Ratnasamy S, Francis P, Handley M, et al. A scalable content-addressablenetwork[J]. Computer Communication Review,2001,31（4）：161-172.
[45] Zhao B Y, Kubiatowicz J, Joseph A D. Tapestry: An infrastructure for fault-tolerant wide-area location and routing[R]. UC Berkeley：Technical Report,2001.
[46] Rowstron, Druschel P. Pastry: Scalable, decentralized object location androuting for large-scale peer-to-peer systems[C]. Proceedings of IFIP/ACMInternational Conference on Distributed Systems Platforms, New York, NY,USA: ACM,2001：329-350.
[47] Sung L G A. System measurement techniques for unstructured peer-to-peersystems[R]. University of Waterloo：Technical Report,2005.
[48] Saroiu S, Gummadi P K, Gribble S D. A Measurement Study of Peer-to-PeerFile Sharing Systems[C]. Proceedings of the Multimedia Computing andNetworking, San Jose: IEEE Press,2002：15.
[49] Stutzbach D, Rejaie R. Capturing accurate snapshots of the Gnutellanetwork[C]. Proceedings of the24th Annual Joint Conference of the IEEEComputer and Communications Societies, Miami: IEEE Press,2005：2825-2830.
[50]王勇,云晓春,李奕飞.对等网络拓扑测量与特征分析[J].软件学报,2008,19（4）：981-992.
[51] Steiner M, En-Najjary T, Biersack E W. A global view of kad[C]. Proceedingsof the7th ACM SIGCOMM conference on Internet measurement, New York,NY, USA: ACM,2007：117-122.
[52] Falkner J, Piatek M, John J P, et al. Profiling a million user dht[C].Proceedings of the7th ACM SIGCOMM conference on Internet measurement,New York, NY, USA: ACM,2007：129-134.
[53] Zhou M, Zhang J, Dai Y. An implementation and optimization for scalableDHT crawler[J]. SCIENCE CHINA(Information Sciences),2010,53（4）：769-779.
[54] Freedman M J, Lakshminarayanan K, Sean R, et al. Non-transitiveconnectivity and DHTs[C]. Proceedings of the2nd conference on Real, LargeDistributed System, USA: USENIX Association,2005：55-60.
[55] Risso F, Baldi M, Morandi O, et al. Lightweight, Payload-Based TrafficClassification: An Experimental Evaluation[C]. Proceedings of IEEE Interna-tional Conference on Communications, Beijing: IEEE Press,2008：5869-5875.
[56] Sen S, Spatscheck O, Wang D. Accurate, Scalable In-Network Identificationof P2P Traffic Using Application Signatures[C]. Proceedings of13thinternational conference on WWW. New York, NY, USA: ACM2004：512-521.
[57] AceNet[EB/OL][2011-04-12]. http://www.acenettech.com.
[58] L7-filter[EBL][2011-04-12]. http://l7-filter.sourceforge.net.
[59] Karagiannis T, Papagiannaki K, Faloutsos M. BLINC: multilevel trafficclassification in the dark[C]. Proceedings of the2005conference onApplications, technologies, architectures, and protocols for computercommunications, New York, NY, USA: ACM,2005：229-240.
[60] Erman J, Arlitt M, Mahanti A. Traffic Classification Using ClusteringAlgorithms[C]. Proceedings of the2006SIGCOMM workshop on Miningnetwork data, New York, NY, USA: ACM,2006：281-286.
[61] McGregor, Hall M, Lorier P, et al. Flow Clustering Using Machine LearningTechniques[C]. Proceedings of the5th Passive and Active MeasurementWorkshop, Antibes Juan-les-Pins, France: Springer,2004：205-214.
[62] Marcell P, Sandor M. Enhanced skype traffic identification[C]. In Proceedingsof the2nd International Conference on Performance EvaluationMethodologies and Tools, New York, NY, USA: ACM,2007：1-9.
[63] Este A, Gringoli F, Salgarelli L. On the stability of the information carried bytraffic flow features at the packet level[J]. ACM SIGCOMM ComputerCommunication Review,2009,39（3）：13-18.
[64] Waxman B M. Routing of multipoint connections[J]. IEEE Journal onSelected Areas in Communications,1988,6（9）：1617-1622.
[65] Doar M B. A better model for generating test networks[C]. Proceedings of theGLOBECOM’96, London: IEEE Press,1996：86-93.
[66] Zegura E W, Calvert K L, Donahoo M J. A quantitative comparison of graph-based models for Internet topology[J]. IEEE/ACM Trans. on Networking,1997,5（6）：770-783.
[67] Faloutsos M, Faloutsos P, Faloutsos C. On power-law relationships of theInternet topology[J]. ACM SIGCOMM Computer Communication Review,1999,29（4）：251-262.
[68] Watts D, Strogatz S. Collective dynamics of ‘small-world’ networks[J].Nature,1998,393（6684）：440-442.
[69] Ripeanu M, Foster I, Iamnitchi A. Mapping the Gnutella network: Propertiesof large-scale peer-to-peer systems and implications for system design[J].IEEE Internet Computing Journal,2002,6（1）：50-57.
[70] Mihajlo. Modeling Peer-To-Peer Network Topologies-Through Small-WorldModels[C]. Proceedings of IX Telecommunications forum telfor, Belgrade,2001.
[71] Stutzbach D, Rejaie R. Characterizing Today's Gnutella Topology[R].Technical Report, Department of Computer Science, University or Oregon,2004.
[72] Adar E, Huberman B. Free Riding on Gnutella[J]. First Monday,2000,5（10）.
[73] Saroiu S, Gummadi K P, R. Dunn J, et al. An analysis of internet contentdelivery systems[J]. SIGOPS Operating Systems Review,2002,36（SI）：315–327.
[74] Liang J, Kumar R, Ross K W. The KaZaA Overlay: A Measurement Study[C].Proceedings of the19th IEEE Annual Computer Communications Workshop,IEEE Press,2004.
[75] Gummadi K P, Dunn R J, Saroiu S, et al. Measurement, modeling, andanalysis of a peer-to-peer file sharing workload[C]. Processings of the SOSP,,New York, NY, USA: ACM,2003.
[76] Karagiannis T, Broido A, Brownlee N, et al. File-sharing in the Internet: Acharacterization of P2P traffic in the backbone[R], Technical Report, UCRiverside,2003.
[77] Pouwelse J A, Garbacki P, Epema D, et al. A measurement study of thebittorrent peer-to-peer file sharing system[R]. Delft University of TechnologyParallel and Distributed Systems Report Series,2004.
[78] Sen S, Wang J. Analyzing peer-to-peer traffic across large networks[J].IEEE/ACM Transactions on Networking,2004,12（2）：219-232.
[79] Bellissimo, Levine B N, Shenoy P. Exploring the use of BitTorrent as thebasis for a large trace repository[R]. University of Massachusetts Amherst:Techocal Report,2004.
[80] Pouwelse J A, Garbacki P, Epema D H J, et al. The Bittorrent P2P File-sharingSystem: Measurements and Analysis[C]. Proceedings of the4th InternationalWorkshop on Peer-to-Peer Systems, Ithaca, USA: LNCS,2005：205-216.
[81] Wang H, Liu J, Xu K. On the Locality of BitTorrent-based Video FileSwarming[C]. Proceedings of the8th international conference on Peer-to-peersystems, New York, NY, USA: ACM,2009：12-18.
[82] Neglia G, Reina G, Zhang H, et al. Availability in BitTorrent Systems[C].Proceedings of the26th IEEE Conference on Computer Communications,Anchorage: IEEE Press,2007：2216-2224.
[83] Izal M, Urvoy-Keller G. Biersack E W, et al. Dissecting BitTorrent: FiveMonths in a Torrent's Lifetime[C]. Proceedings of Passive and ActiveMeasurements, New York, NY, USA: ACM,2004：1-11.
[84] Guo L, Chen S Q, Zhen X, et al. Measurements, analysis, and modeling ofBitTorrent-like systems[C]. Proceedings of of the5th ACM SIGCOMMconference on Internet Measurement, New York, NY, USA: ACM,2005：1-14.
[85] Stutzbach D, Rejaie R. Understanding churn in peer-to-peer networks[C].Proceedings of the6th ACM SIGCOMM conference on Internet measurement,Rio de Janeriro, New York, NY, USA: ACM：189-202.
[86] Felber P A, Biersack E W. Self-scaling networks for content distribution[C].Proceedings of the International Workshop on Self-Properties in ComplexInformation Systems, Bertinoro, Italy,2004.
[87] Bharambe R, Herley C, Padmanabhan V N. Analyzing and Improving aBitTorrent Networks Performance Mechanisms[C]. Proceedings of25th IEEEInternational Conference on Computer Communications, Barcelona: IEEEPress,2006：1-12.
[88] Gkantsidis, Rodriguez P R. Network Coding for Large Scale ContentDistribution[C]. Proceedings of the24th IEEE Conference on ComputerCommunications, Miami: IEEE Press,2005：2235-2245.
[89] Legout, Urvoy-Keller G, Michiardi P. Rarest First and Choke Algorithms AreEnough[C]. Proceedings of the6th ACM SIGCOMM conference on Internetmeasurement, New York, NY, USA: ACM,2006：203-216.
[90] Dale, Liu J. A Measurement Study of Piece Population in BitTorrent[C].Proceedings of Global Telecommunications Conference, Washington: IEEEPress,2007：405-410.
[91] Liang J, Naoumov N, Ross K W. The Index Poisoning Attack in P2P File-Sharing Systems[C]. Proceedings of the25th Annual IEEE Conference onComputer Communications, Barcelona: IEEE Press,2006：1-12.
[92] Liang J, Kumar R, Xi Y, et al. Pollution in P2P File Sharing Systems[C].Proceedings of the24th Annual IEEE Conference on ComputerCommunications, Miami: IEEE Press,2005：1174-1185.
[93] Sit E, Morris R T. Security Considerations for Peer-to-Peer Distributed HashTables[C]. Proceedings of the First International Workshop on Peer-to-PeerSystems, Cambridge: LNCS,2002：261-269.
[94] Douceur J R. The sybil attack[C]. Proceedings of the First InternationalWorkshop on Peer-to-Peer Systems, Cambridge: LNCS,2002：251-260.
[95] Media Defender[EB/OL][2011-05-19]. http://www.mediadefender.com
[96] Safenet[EB/OL][2011-05-19]. http://www.safenet-inc.com
[97] Naoumov N, Ross K. Exploiting P2P systems for DDoS attacks[C].Proceedings of the1st international conference on Scalable informationsystems, New York, NY, USA: ACM,2006：47-53.
[98] Zhou L, Zhang L, Mcsherry F, et al. A First Look at Peer-to-Peer Worms:Threats and Defenses[C]. Proceedings of International Symposium on Peer-to-peer Systems, New York, NY, USA: ACM,2005.
[99] Christin N, Weigend A, Chuang J. Content availability, Pollution andPoisoning in Peer-to-Peer File Sharing networks[C]. Proceedings of the6thACM conference on Electronic commerce, New York, NY, USA: ACM,2005：68-77.
[100] Steiner M, En-najjary T, Biersack E W. Exploiting KAD: Possible uses andmisuses[J]. ACM SIGCOMM Computer Communication Review,2007,37（5）：65-70.
[101] Dhungel P, Wu D, Schonhorst B, et al. A measurement study of attacks onBitTorrent leechers[C]. Proceedings of the7th international conference onPeer-to-peer systems, Tampa Bay: LNCS,2008：7-14.
[102] Cohen. Incentives build robustness in BitTorrent[C]. Proceedings of the1stWorkshop on Economics of Peer-to-Peer Systems,2003.
[103] Jun S, Ahamad M. Incentives in BitTorrent induce free riding[C].Proceedings of the2005ACM SIGCOMM workshop on Economics of peer-to-peer systems, New York, NY, USA: ACM,2005：116-121.
[104] Liogkas N, Nelson R, Kohler E, et al. Exploiting BitTorrent for fun (but notprofit)[C]. Proceedings of the5th International Workshop on Peer-to-PeerSystems, Santa Barbara: LNCS,2006.
[105] Locher T, Moor P, Schmid S, et al. Free Riding in BitTorrent is Cheap[C].Proceedings of HotNets-V. New York, NY, USA: ACM,2006：85-90.
[106] Sirivianos M, Park J H, Chen R, et al. Free-riding in BitTorrent networks withthe large view exploit[C]. Proceedings of the5th International Workshop onPeer-to-Peer Systems, LCNS,2007.
[107] Piatek M, Isdal T, Anderson T, et al. Do incentives build robustness inBitTorrent[C]? Proceedings of the4th USENIX Symposium on NetworkedSystems Design&Implementation, USA: USENIX Association,2007：1-14.
[108] Konrath M A, Barcellos M P, Mansilha R B. Attacking a Swarm with a Bandof Liars: evaluating the impact of attacks on BitTorrent[C]. Proceedings of the7th IEEE International Conference on Peer-to-Peer Computing, Galway: IEEEPress,2007：37-44.
[109] Defrawy K E, Gjoka M, Markopoulou A. BotTorrent: misusing BitTorrent tolaunch DDoS attacks[C]. Proceedings of the3rd USENIX workshop on Stepsto reducing unwanted traffic on the internet, USA: USENIX Association,Santa Clara, CA,2007：1-6.
[110] Sia K C. DDoS Vulnerability Analysis of BitTorrent Protocol[R]. UCLA:Techical Report,2006.
[111] Parker, The True Picture of Peer-To-Peer File-Sharing[C]. Proceedings ofIEEE10th Int'l Workshop on Web Content Caching and Distribution, SophiaAntipolis: IEEE Press,2005.
[112] Azureus[EB/OL][2010-12-09]. http://azureus.sourceforge.net.
[113] Yang X, Veciana G D. Service Capacity of Peer-to-Peer Networks[C].Proceedings of the23th AnnualJoint Conference of the IEEE Computer andCommunications Societies, IEEE Press,2004：2242-2252.
[114] Qiu D, Srikant R. Modeling and Performance Analysis of BitTorrent-likePeer-to-Peer Networks[C]. Proceedings of the2004conference Applications,technologies, architectures, and protocols for computer communications, NewYork, NY, USA: ACM,2004：367-378.
[115] Fan B, Chiu D, Lui J C S. Stochastic Differential Equation Approach to ModelBitTorrent-like P2P Systems[C]. Proceedings of IEEE InternationalConference on Communications, Barcelona: IEEE Press,2006：915-920.
[116] Tewari S, Kleinrock L. Optimal search performance in unstructured peer-to-peer networks with clustered demands[J]. IEEE Journal on Selected Areas inCommunications,2007,25（1）：84-95.
[117] Ipoque. Internet Study2008/2009[EB/OL][2011-04-05]. http://www.ipoque.com/resour ces/internet-studies/internet-study-2008_2009.
[118] Labovitz, Johnson S I, McPherson D, et al. Internet Inter-Domain Traffic[C].Proceedings of the ACM SIGCOMM2010conference on SIGCOMM, NewYork, NY, USA: ACM,2010：75-86.
[119] Piatek M, Madhyastha H V, John J P, et al. Pitfalls for ISP-friendly P2Pdesign[C]. Proceedings of8th ACM Workshop on Hot Topics in Networks,New York, NY, USA: ACM,2009.
[120] Dischinger M, Mislove A, Haeberlen A, et al. Detecting bittorrent blocking[C]. Proceedings of the8th ACM SIGCOMM conference on Internetmeasurement, New York, NY, USA: ACM,2008：3-8.
[121] Packet Forgery by ISPs: A Report on the Comcast Affair[EB/OL][2010-10-19].http://www.eff.org/wp/packet-forgery-isps-report-comcast-affair
[122]徐鹏，刘琼，林森.改进的对等网络流量传输层识别方法[J].计算机研究与发展，2008，45（5）：794-802.
[123] Constantinou, Mavrommatis P. Identifying Known and Unknown Peer-to-PeerTraffic[C]. Proceedings of the5th IEEE International Symposium on NetworkComputing and Applications, Washington: IEEE Press,2006：93-102.
[124]周丽娟. P2P流媒体识别方法的研究[D].武汉：华中科技大学,2008.
[125] Gallagher, Iliofotou M, Rad T E, et al. Link homophily in the applicationlayer and its usage in traffic classification[C]. Proceedings of the29thconference on Information communications, Piscataway: IEEE Press,2010：221-225.
[126] Liu Q, Xu P, Yang H T, et al. Research on measurement of peer-to-peer filesharing system[J]. Journal of Software,2006,17（10）：2131-2140.
[127] Xu J, Kumar A, Yu X X. On the fundamental trafeoffs between routing tablesize and network diameter in peer-to-peer networks[J]. IEEE Journal onSelected Area in Communication,2004,22（1）：151-163.
[128]李东升，卢锡城. P2P网络中常量度数常量拥塞的DHT方法研究[J].中国科学E辑，2004，34（12）：1337-1358.
[129]陈贵海，须成忠，沈海英，等.一种新的常数度数的P2P覆盖网络[J].计算机学报，2005，28（7）：1084-1095.
[130] Gummadi K, Gummadi R, Gribble S, et al. The Impact of DHT RoutingGeometry on Resilience and Proximity[C]. Proceedings of ACM Sigcomm2003, New York, NY, USA: ACM,2003：381-394.
[131] Li J, Stribling J, Morris R, et al. A performance vs. cost framework forevaluating dht design tradeoffs under churn[C]. Proceedings of the24thAnnual Joint Conference of the IEEE Computer and CommunicationsSocieties, Miami: IEEE Press,2005：225-236.
[132] Stutzbach, Rejaie R. Improving Lookup Performance over a Widely-DeployedDHT[C]. Proceedings of the25th IEEE Conference on ComputerCommunications, Barcelona: IEEE Press,2006：1-12.
[133] Wu, Ye T, Ng K. Analytical Study on Improving DHT Lookup Performanceunder Churn[C]. Proceedings of the6th IEEE International Conference onPeer-to-Peer Computing, IEEE Press,2006：249-258.
[134] Zhang R, Hu Y C, Druschel P. Optimizing routing in structured peer-to-peeroverlay networks using routing table redundancy[C]. Proceedings of the NinthIEEE Workshop on Future Trends of Distributed Computing systems, IEEEPress,2003：315-361.
[135] Ren S, Guo L, Jiang S, et al. SAT-Match: A self-adaptive topology matchingmethod to acheive low lookup latency in structured P2P overlay networks[C].Proceedings of the18th International Parallel and Distributed ProcessingSymposium, IEEE Press,2004：83-91.
[136] Castro M, Druschel P, Ganesh A, et al. Security Routing for structured peer-to-peer overlay networks[C]. Proceedings of the5th USENIX Symposium onOperating Systems Design and Implementation, USA: USENIX Association,2002：299-314.
[137] Borisov N. Computational Puzzles as Sybil Defenses[C]. Proceedings of the6th IEEE International Conference on Peer-to-Peer Computing, New York, NY,USA: ACM,2006:171-176.
[138] Varun T C, Kacholia V, Sankararaman S, et al. Induced Churn as Shelter fromRouting-Table Poisoning[C]. Proceedings of13th Annual Network andDistributed System Security Symposium,2006.
[139] Singh, Ngan T-Wan, Druschel P, et al. Eclipse Attacks on Overlay Networks:Threats and Defenses[C]. Proceedings of25th IEEE International Conferenceon Computer Communications, Barcelona: IEEE Press,2006：161-172.
[140] Wei H, Fedak G, Cappello F. Collaborative data distribution with bittorrent forcomputational desktop grids[C]. Proceedings of the4th InternationalSymposium on Parallel and Distributed Computing, New York, NY, USA:ACM,2005：250-257.
[141] Parvez N, Williamson C, Mahanti A, et al. Analysis of bittorrent-likeprotocols for on-demand stored media streaming[C]. Proceedings of the2008ACM SIGMETRICS international conference on Measurement and modelingof computer systems, New York, NY, USA: ACM,2008：301-312.
[142] Levin, LaCurts K, Spring N, et al. Bittorrent is an auction: analyzing andimproving bittorrent's incentives[C]. Proceedings of the ACM SIGCOMM2008conference on Data communication, New York, NY, USA: ACM,2008：243-254.
[143] Massoulié L, Vojnovi′c M. Coupon Replication Systems[C]. Proceedings ofthe2005ACM SIGMETRICS international conference on Measurement andmodeling of computer systems, New York, NY, USA: ACM,2005：2-13.
[144]史建焘，张宏莉，方滨兴. BitTorrent假块污染攻击的对抗方法研究[J].计算机学报,2011,34（1）：15-24.
[145] BitComet[EB/OL][2011-05-12]. http://www.bitcomet.com/index-zh-cn.php
[146] Bitspirit[EB/OL][2011-05-12]. http://www.bitspirit.cc
[2] Berners-Lee T J, et al. The World Wide Web[J]. Communications of the ACM,1994,37（8）：76-82.
[3] ANSI T1.413-1998. Network and Customer Installation Interfaces–Asymmetric Digital Subscriber Line (ADSL) Metallic Interface, AmericanNational Standards Institute1998.
[4] Cisco Company. Cisco Visual Networking Index: Forecast and Methodology,2009-2014[EB/OL][2011-04-25]. http://www.cisco.com/en/US/solutions/collateral/ns341/ns525/ns537/ns705/ns827/white_paper_c11481360_ns827_Networking_Solutions_White_Paper.html
[5]中国互联网络信息中心.第26次中国互联网络发展状况统计报告[EB/OL][2011-03-11]. http://www.cnnic.net.cn/xzzx/tjbgxz/201010/t20101020_16004.html
[6] BitTorrent[EB/OL][2010-11-11]. http://bitconjurer.org/BitTorrent.
[7] eMule[EB/OL][2010-12-5]. http://www.emule-project.net.
[8] Chen H, Yang M, Han J, et al. Maze: a Social Peer-to-peer Network[C].Proceedings of the IEEE International Conference on E-CommerceTechnology for Dynamic E-Business, Beijing: IEEE Press,2004：290-293.
[9] Kubiatowicz J, Bindel D, Chen Y, et al. OceanStore: An Architecture forGlobal-Scale Persistent Storage[C]. Proceedings of the9th InternationalConference on Architectural Support for Programming Languages andOperating Systems, New York, NY, USA: ACM,2000,35（11）：190-201.
[10] Zheng W, Hu J, Li M. Granary: Architecture of Object Oriented InternetStorage Service[C]. Proceedings of the IEEE International Conference on E-Commerce Technology for Dynamic E-Business, Beijing: IEEE Press,2004：294-297.
[11] Huang Y, Fu T Z J, Chiu D, et al. Challenges, design and analysis of a large-scale p2p-vod system[C]. Proceedings of the ACM SIGCOMM2008conference on Data communication, New York, NY, USA: ACM,2008：375-388.
[12] Liao X, Jin H, Liu Y, et al. AnySee: Peer-to-Peer Live Streaming[C].Proceedings of the25th IEEE International Conference on ComputerCommunications, Barcelona: IEEE Press,2006：1-10.
[13] Skype[EB/OL][2011-03-03]. http://www.skype.com.
[14] SETI@home[EB/OL][2011-03-03]. http://setiathome.berkeley.edu.
[15] Napster[EB/OL][2011-03-03]. http://www.napster.com
[16] Gnutella[EB/OL][2011-03-03]. http://rfc-gnutella.sourceforge.net.
[17] KaZaA[EB/OL][2011-03-03]. http://www.kazaa.com.
[18] Maymounkov P, Mazières D. Kademlia: A Peer-to-Peer Information SystemBased on the XOR Metric[C]. Proceedings of the First International Workshopon Peer-to-Peer System, Cambridge, MA, USA: Springer-Verlag,2002：53-65.
[19] Xie H, Yang Y R, Krishnamurthy A, et al. P4P: provider portal forapplications[C]. Proceedings of the ACM SIGCOMM2008conference onData communication, New York, NY, USA: ACM,2008：351-362.
[20] Tuotu[EB/OL][2011-03-04]. http://www.tuotu.com.
[21]王继龙，吴建平. Internet行为学[EB/OL][2011-03-16]. http://wenku.baidu.com/view/31ceb01252d380eb62946da0.html
[22]程光，龚俭，丁伟.网络测量及行为学研究综述[J].计算机工程与应用，2004，40（27）：1-8.
[23] Paxson V E. Measurements and Analysisof End-to-End Internet Dynamics[D].Berkeley: University of California,1997.
[24] Mahdavi J, Paxson V. IPPM Metrics for Measuring Connectivity[R]. RFC2678, Sep1999.
[25] Almes G, Kalidindi S, Zekauskas M. A One-way Delay Metric for IPPM[R].RFC2679, Sep1999.
[26] Almes G, Kalidindi S, Zekauskas M. A One-way Packet Loss Metric forIPPM[R]. RFC2680, Sep1999.
[27] Almes G, Kalidindi S, Zekauskas M. A Round-trip Delay Metric for IPPM[R].RFC2681, Sep1999.
[28] Leland W E, Taqqu M S, W. Willinger, et al. On the self-similar nature ofethernet traffic[J]. IEEE/ACM Transaction on Networking,1994,2（1）：1-15.
[29] Zhang Y, Paxson V, Shenker S. The stationarity of internet path properties:Routing, loss, and throughput[R]. Technical report, ACIRI,2000.
[30] Paxson V. End-to-end routing behavior in the internet[J]. ACM SIGCOMMComputer Communication Review, ACM, New York, NY, USA,2006：41-56.
[31] Shaikh A, Varma A, Kalampoukas L, et al. Routing stability in congestednetworks: experimentation and analysis[C]. Proceedings of the conference onApplications, Technologies, Architectures, and Protocols for ComputerCommunication, New York, NY, USA: ACM,2000：163-174.
[32]裴昌幸，等,现代通信系统与网络测量[M].北京：人民邮电出版社，2008：70-71.
[33] Horváth, Telek M. A Markovian Point Process Exhibiting MultifractalBehavior and its Application to Traffic Modeling[C]. Proceedings of4thInternational Conference on Matrix-analytic Methods in Stochastic Models,Adelaide, Australia,2002：1-12.
[34] NS-2[EB/OL][2010-12-01]. http://www.isi.edu/nsnam/ns/.
[35] Oram A. Peer-to-Peer Harnessing the power of disruptive technologies[M].California: O'Reilly Media,2001：1-20
[36] Lua E K, Crowcroft J, Pias M, et al. A survey and comparison of peer-to-peeroverlay network schemes[J]. Journal of IEEE Communications Survey andTutorial,2005,7（2）：72-93.
[37]郑纬民,胡进锋,代亚非，等.对等计算研究概论[M].中国计算机学会通讯,2005：38-51.
[38]张宇翔,杨冬,张宏科. P2P网络中Churn问题研究[J].软件学报,2009,20（5）：1362-1376.
[39] eDonkey2000[EB/OL][2011-01-12]. http://emulefans.com.
[40] Borland J, RIAA threat may be slowing file swapping[EB/OL][2010-10-15].http://news.cnet.com/2100-1027-1025684.html.
[41] Lv Q, Cao P, Cohen E, et al. Search and replication in unstructured peer-to-peer networks[C]. Proceedings of the16th international conference onSupercomputing, New York, NY, USA: ACM,2002：84-95.
[42] Gkantsidis C, Mihail M, Saberi A. Random walks in peer-to-peer networks:algorithms and evaluation[J]. Performance Evaluation, HongKong, CN,2006,63（3）：241-263.
[43] Stoica, Morris R, Karger D, et al. Chord: A Scalable Peer-to-peer LookupService for Internet Applications[C]. Proceedings of the2001conference onApplications, technologies, architectures, and protocols for computercommunications, New York, NY, USA: ACM,2001：149-160.
[44] Ratnasamy S, Francis P, Handley M, et al. A scalable content-addressablenetwork[J]. Computer Communication Review,2001,31（4）：161-172.
[45] Zhao B Y, Kubiatowicz J, Joseph A D. Tapestry: An infrastructure for fault-tolerant wide-area location and routing[R]. UC Berkeley：Technical Report,2001.
[46] Rowstron, Druschel P. Pastry: Scalable, decentralized object location androuting for large-scale peer-to-peer systems[C]. Proceedings of IFIP/ACMInternational Conference on Distributed Systems Platforms, New York, NY,USA: ACM,2001：329-350.
[47] Sung L G A. System measurement techniques for unstructured peer-to-peersystems[R]. University of Waterloo：Technical Report,2005.
[48] Saroiu S, Gummadi P K, Gribble S D. A Measurement Study of Peer-to-PeerFile Sharing Systems[C]. Proceedings of the Multimedia Computing andNetworking, San Jose: IEEE Press,2002：15.
[49] Stutzbach D, Rejaie R. Capturing accurate snapshots of the Gnutellanetwork[C]. Proceedings of the24th Annual Joint Conference of the IEEEComputer and Communications Societies, Miami: IEEE Press,2005：2825-2830.
[50]王勇,云晓春,李奕飞.对等网络拓扑测量与特征分析[J].软件学报,2008,19（4）：981-992.
[51] Steiner M, En-Najjary T, Biersack E W. A global view of kad[C]. Proceedingsof the7th ACM SIGCOMM conference on Internet measurement, New York,NY, USA: ACM,2007：117-122.
[52] Falkner J, Piatek M, John J P, et al. Profiling a million user dht[C].Proceedings of the7th ACM SIGCOMM conference on Internet measurement,New York, NY, USA: ACM,2007：129-134.
[53] Zhou M, Zhang J, Dai Y. An implementation and optimization for scalableDHT crawler[J]. SCIENCE CHINA(Information Sciences),2010,53（4）：769-779.
[54] Freedman M J, Lakshminarayanan K, Sean R, et al. Non-transitiveconnectivity and DHTs[C]. Proceedings of the2nd conference on Real, LargeDistributed System, USA: USENIX Association,2005：55-60.
[55] Risso F, Baldi M, Morandi O, et al. Lightweight, Payload-Based TrafficClassification: An Experimental Evaluation[C]. Proceedings of IEEE Interna-tional Conference on Communications, Beijing: IEEE Press,2008：5869-5875.
[56] Sen S, Spatscheck O, Wang D. Accurate, Scalable In-Network Identificationof P2P Traffic Using Application Signatures[C]. Proceedings of13thinternational conference on WWW. New York, NY, USA: ACM2004：512-521.
[57] AceNet[EB/OL][2011-04-12]. http://www.acenettech.com.
[58] L7-filter[EBL][2011-04-12]. http://l7-filter.sourceforge.net.
[59] Karagiannis T, Papagiannaki K, Faloutsos M. BLINC: multilevel trafficclassification in the dark[C]. Proceedings of the2005conference onApplications, technologies, architectures, and protocols for computercommunications, New York, NY, USA: ACM,2005：229-240.
[60] Erman J, Arlitt M, Mahanti A. Traffic Classification Using ClusteringAlgorithms[C]. Proceedings of the2006SIGCOMM workshop on Miningnetwork data, New York, NY, USA: ACM,2006：281-286.
[61] McGregor, Hall M, Lorier P, et al. Flow Clustering Using Machine LearningTechniques[C]. Proceedings of the5th Passive and Active MeasurementWorkshop, Antibes Juan-les-Pins, France: Springer,2004：205-214.
[62] Marcell P, Sandor M. Enhanced skype traffic identification[C]. In Proceedingsof the2nd International Conference on Performance EvaluationMethodologies and Tools, New York, NY, USA: ACM,2007：1-9.
[63] Este A, Gringoli F, Salgarelli L. On the stability of the information carried bytraffic flow features at the packet level[J]. ACM SIGCOMM ComputerCommunication Review,2009,39（3）：13-18.
[64] Waxman B M. Routing of multipoint connections[J]. IEEE Journal onSelected Areas in Communications,1988,6（9）：1617-1622.
[65] Doar M B. A better model for generating test networks[C]. Proceedings of theGLOBECOM’96, London: IEEE Press,1996：86-93.
[66] Zegura E W, Calvert K L, Donahoo M J. A quantitative comparison of graph-based models for Internet topology[J]. IEEE/ACM Trans. on Networking,1997,5（6）：770-783.
[67] Faloutsos M, Faloutsos P, Faloutsos C. On power-law relationships of theInternet topology[J]. ACM SIGCOMM Computer Communication Review,1999,29（4）：251-262.
[68] Watts D, Strogatz S. Collective dynamics of ‘small-world’ networks[J].Nature,1998,393（6684）：440-442.
[69] Ripeanu M, Foster I, Iamnitchi A. Mapping the Gnutella network: Propertiesof large-scale peer-to-peer systems and implications for system design[J].IEEE Internet Computing Journal,2002,6（1）：50-57.
[70] Mihajlo. Modeling Peer-To-Peer Network Topologies-Through Small-WorldModels[C]. Proceedings of IX Telecommunications forum telfor, Belgrade,2001.
[71] Stutzbach D, Rejaie R. Characterizing Today's Gnutella Topology[R].Technical Report, Department of Computer Science, University or Oregon,2004.
[72] Adar E, Huberman B. Free Riding on Gnutella[J]. First Monday,2000,5（10）.
[73] Saroiu S, Gummadi K P, R. Dunn J, et al. An analysis of internet contentdelivery systems[J]. SIGOPS Operating Systems Review,2002,36（SI）：315–327.
[74] Liang J, Kumar R, Ross K W. The KaZaA Overlay: A Measurement Study[C].Proceedings of the19th IEEE Annual Computer Communications Workshop,IEEE Press,2004.
[75] Gummadi K P, Dunn R J, Saroiu S, et al. Measurement, modeling, andanalysis of a peer-to-peer file sharing workload[C]. Processings of the SOSP,,New York, NY, USA: ACM,2003.
[76] Karagiannis T, Broido A, Brownlee N, et al. File-sharing in the Internet: Acharacterization of P2P traffic in the backbone[R], Technical Report, UCRiverside,2003.
[77] Pouwelse J A, Garbacki P, Epema D, et al. A measurement study of thebittorrent peer-to-peer file sharing system[R]. Delft University of TechnologyParallel and Distributed Systems Report Series,2004.
[78] Sen S, Wang J. Analyzing peer-to-peer traffic across large networks[J].IEEE/ACM Transactions on Networking,2004,12（2）：219-232.
[79] Bellissimo, Levine B N, Shenoy P. Exploring the use of BitTorrent as thebasis for a large trace repository[R]. University of Massachusetts Amherst:Techocal Report,2004.
[80] Pouwelse J A, Garbacki P, Epema D H J, et al. The Bittorrent P2P File-sharingSystem: Measurements and Analysis[C]. Proceedings of the4th InternationalWorkshop on Peer-to-Peer Systems, Ithaca, USA: LNCS,2005：205-216.
[81] Wang H, Liu J, Xu K. On the Locality of BitTorrent-based Video FileSwarming[C]. Proceedings of the8th international conference on Peer-to-peersystems, New York, NY, USA: ACM,2009：12-18.
[82] Neglia G, Reina G, Zhang H, et al. Availability in BitTorrent Systems[C].Proceedings of the26th IEEE Conference on Computer Communications,Anchorage: IEEE Press,2007：2216-2224.
[83] Izal M, Urvoy-Keller G. Biersack E W, et al. Dissecting BitTorrent: FiveMonths in a Torrent's Lifetime[C]. Proceedings of Passive and ActiveMeasurements, New York, NY, USA: ACM,2004：1-11.
[84] Guo L, Chen S Q, Zhen X, et al. Measurements, analysis, and modeling ofBitTorrent-like systems[C]. Proceedings of of the5th ACM SIGCOMMconference on Internet Measurement, New York, NY, USA: ACM,2005：1-14.
[85] Stutzbach D, Rejaie R. Understanding churn in peer-to-peer networks[C].Proceedings of the6th ACM SIGCOMM conference on Internet measurement,Rio de Janeriro, New York, NY, USA: ACM：189-202.
[86] Felber P A, Biersack E W. Self-scaling networks for content distribution[C].Proceedings of the International Workshop on Self-Properties in ComplexInformation Systems, Bertinoro, Italy,2004.
[87] Bharambe R, Herley C, Padmanabhan V N. Analyzing and Improving aBitTorrent Networks Performance Mechanisms[C]. Proceedings of25th IEEEInternational Conference on Computer Communications, Barcelona: IEEEPress,2006：1-12.
[88] Gkantsidis, Rodriguez P R. Network Coding for Large Scale ContentDistribution[C]. Proceedings of the24th IEEE Conference on ComputerCommunications, Miami: IEEE Press,2005：2235-2245.
[89] Legout, Urvoy-Keller G, Michiardi P. Rarest First and Choke Algorithms AreEnough[C]. Proceedings of the6th ACM SIGCOMM conference on Internetmeasurement, New York, NY, USA: ACM,2006：203-216.
[90] Dale, Liu J. A Measurement Study of Piece Population in BitTorrent[C].Proceedings of Global Telecommunications Conference, Washington: IEEEPress,2007：405-410.
[91] Liang J, Naoumov N, Ross K W. The Index Poisoning Attack in P2P File-Sharing Systems[C]. Proceedings of the25th Annual IEEE Conference onComputer Communications, Barcelona: IEEE Press,2006：1-12.
[92] Liang J, Kumar R, Xi Y, et al. Pollution in P2P File Sharing Systems[C].Proceedings of the24th Annual IEEE Conference on ComputerCommunications, Miami: IEEE Press,2005：1174-1185.
[93] Sit E, Morris R T. Security Considerations for Peer-to-Peer Distributed HashTables[C]. Proceedings of the First International Workshop on Peer-to-PeerSystems, Cambridge: LNCS,2002：261-269.
[94] Douceur J R. The sybil attack[C]. Proceedings of the First InternationalWorkshop on Peer-to-Peer Systems, Cambridge: LNCS,2002：251-260.
[95] Media Defender[EB/OL][2011-05-19]. http://www.mediadefender.com
[96] Safenet[EB/OL][2011-05-19]. http://www.safenet-inc.com
[97] Naoumov N, Ross K. Exploiting P2P systems for DDoS attacks[C].Proceedings of the1st international conference on Scalable informationsystems, New York, NY, USA: ACM,2006：47-53.
[98] Zhou L, Zhang L, Mcsherry F, et al. A First Look at Peer-to-Peer Worms:Threats and Defenses[C]. Proceedings of International Symposium on Peer-to-peer Systems, New York, NY, USA: ACM,2005.
[99] Christin N, Weigend A, Chuang J. Content availability, Pollution andPoisoning in Peer-to-Peer File Sharing networks[C]. Proceedings of the6thACM conference on Electronic commerce, New York, NY, USA: ACM,2005：68-77.
[100] Steiner M, En-najjary T, Biersack E W. Exploiting KAD: Possible uses andmisuses[J]. ACM SIGCOMM Computer Communication Review,2007,37（5）：65-70.
[101] Dhungel P, Wu D, Schonhorst B, et al. A measurement study of attacks onBitTorrent leechers[C]. Proceedings of the7th international conference onPeer-to-peer systems, Tampa Bay: LNCS,2008：7-14.
[102] Cohen. Incentives build robustness in BitTorrent[C]. Proceedings of the1stWorkshop on Economics of Peer-to-Peer Systems,2003.
[103] Jun S, Ahamad M. Incentives in BitTorrent induce free riding[C].Proceedings of the2005ACM SIGCOMM workshop on Economics of peer-to-peer systems, New York, NY, USA: ACM,2005：116-121.
[104] Liogkas N, Nelson R, Kohler E, et al. Exploiting BitTorrent for fun (but notprofit)[C]. Proceedings of the5th International Workshop on Peer-to-PeerSystems, Santa Barbara: LNCS,2006.
[105] Locher T, Moor P, Schmid S, et al. Free Riding in BitTorrent is Cheap[C].Proceedings of HotNets-V. New York, NY, USA: ACM,2006：85-90.
[106] Sirivianos M, Park J H, Chen R, et al. Free-riding in BitTorrent networks withthe large view exploit[C]. Proceedings of the5th International Workshop onPeer-to-Peer Systems, LCNS,2007.
[107] Piatek M, Isdal T, Anderson T, et al. Do incentives build robustness inBitTorrent[C]? Proceedings of the4th USENIX Symposium on NetworkedSystems Design&Implementation, USA: USENIX Association,2007：1-14.
[108] Konrath M A, Barcellos M P, Mansilha R B. Attacking a Swarm with a Bandof Liars: evaluating the impact of attacks on BitTorrent[C]. Proceedings of the7th IEEE International Conference on Peer-to-Peer Computing, Galway: IEEEPress,2007：37-44.
[109] Defrawy K E, Gjoka M, Markopoulou A. BotTorrent: misusing BitTorrent tolaunch DDoS attacks[C]. Proceedings of the3rd USENIX workshop on Stepsto reducing unwanted traffic on the internet, USA: USENIX Association,Santa Clara, CA,2007：1-6.
[110] Sia K C. DDoS Vulnerability Analysis of BitTorrent Protocol[R]. UCLA:Techical Report,2006.
[111] Parker, The True Picture of Peer-To-Peer File-Sharing[C]. Proceedings ofIEEE10th Int'l Workshop on Web Content Caching and Distribution, SophiaAntipolis: IEEE Press,2005.
[112] Azureus[EB/OL][2010-12-09]. http://azureus.sourceforge.net.
[113] Yang X, Veciana G D. Service Capacity of Peer-to-Peer Networks[C].Proceedings of the23th AnnualJoint Conference of the IEEE Computer andCommunications Societies, IEEE Press,2004：2242-2252.
[114] Qiu D, Srikant R. Modeling and Performance Analysis of BitTorrent-likePeer-to-Peer Networks[C]. Proceedings of the2004conference Applications,technologies, architectures, and protocols for computer communications, NewYork, NY, USA: ACM,2004：367-378.
[115] Fan B, Chiu D, Lui J C S. Stochastic Differential Equation Approach to ModelBitTorrent-like P2P Systems[C]. Proceedings of IEEE InternationalConference on Communications, Barcelona: IEEE Press,2006：915-920.
[116] Tewari S, Kleinrock L. Optimal search performance in unstructured peer-to-peer networks with clustered demands[J]. IEEE Journal on Selected Areas inCommunications,2007,25（1）：84-95.
[117] Ipoque. Internet Study2008/2009[EB/OL][2011-04-05]. http://www.ipoque.com/resour ces/internet-studies/internet-study-2008_2009.
[118] Labovitz, Johnson S I, McPherson D, et al. Internet Inter-Domain Traffic[C].Proceedings of the ACM SIGCOMM2010conference on SIGCOMM, NewYork, NY, USA: ACM,2010：75-86.
[119] Piatek M, Madhyastha H V, John J P, et al. Pitfalls for ISP-friendly P2Pdesign[C]. Proceedings of8th ACM Workshop on Hot Topics in Networks,New York, NY, USA: ACM,2009.
[120] Dischinger M, Mislove A, Haeberlen A, et al. Detecting bittorrent blocking[C]. Proceedings of the8th ACM SIGCOMM conference on Internetmeasurement, New York, NY, USA: ACM,2008：3-8.
[121] Packet Forgery by ISPs: A Report on the Comcast Affair[EB/OL][2010-10-19].http://www.eff.org/wp/packet-forgery-isps-report-comcast-affair
[122]徐鹏，刘琼，林森.改进的对等网络流量传输层识别方法[J].计算机研究与发展，2008，45（5）：794-802.
[123] Constantinou, Mavrommatis P. Identifying Known and Unknown Peer-to-PeerTraffic[C]. Proceedings of the5th IEEE International Symposium on NetworkComputing and Applications, Washington: IEEE Press,2006：93-102.
[124]周丽娟. P2P流媒体识别方法的研究[D].武汉：华中科技大学,2008.
[125] Gallagher, Iliofotou M, Rad T E, et al. Link homophily in the applicationlayer and its usage in traffic classification[C]. Proceedings of the29thconference on Information communications, Piscataway: IEEE Press,2010：221-225.
[126] Liu Q, Xu P, Yang H T, et al. Research on measurement of peer-to-peer filesharing system[J]. Journal of Software,2006,17（10）：2131-2140.
[127] Xu J, Kumar A, Yu X X. On the fundamental trafeoffs between routing tablesize and network diameter in peer-to-peer networks[J]. IEEE Journal onSelected Area in Communication,2004,22（1）：151-163.
[128]李东升，卢锡城. P2P网络中常量度数常量拥塞的DHT方法研究[J].中国科学E辑，2004，34（12）：1337-1358.
[129]陈贵海，须成忠，沈海英，等.一种新的常数度数的P2P覆盖网络[J].计算机学报，2005，28（7）：1084-1095.
[130] Gummadi K, Gummadi R, Gribble S, et al. The Impact of DHT RoutingGeometry on Resilience and Proximity[C]. Proceedings of ACM Sigcomm2003, New York, NY, USA: ACM,2003：381-394.
[131] Li J, Stribling J, Morris R, et al. A performance vs. cost framework forevaluating dht design tradeoffs under churn[C]. Proceedings of the24thAnnual Joint Conference of the IEEE Computer and CommunicationsSocieties, Miami: IEEE Press,2005：225-236.
[132] Stutzbach, Rejaie R. Improving Lookup Performance over a Widely-DeployedDHT[C]. Proceedings of the25th IEEE Conference on ComputerCommunications, Barcelona: IEEE Press,2006：1-12.
[133] Wu, Ye T, Ng K. Analytical Study on Improving DHT Lookup Performanceunder Churn[C]. Proceedings of the6th IEEE International Conference onPeer-to-Peer Computing, IEEE Press,2006：249-258.
[134] Zhang R, Hu Y C, Druschel P. Optimizing routing in structured peer-to-peeroverlay networks using routing table redundancy[C]. Proceedings of the NinthIEEE Workshop on Future Trends of Distributed Computing systems, IEEEPress,2003：315-361.
[135] Ren S, Guo L, Jiang S, et al. SAT-Match: A self-adaptive topology matchingmethod to acheive low lookup latency in structured P2P overlay networks[C].Proceedings of the18th International Parallel and Distributed ProcessingSymposium, IEEE Press,2004：83-91.
[136] Castro M, Druschel P, Ganesh A, et al. Security Routing for structured peer-to-peer overlay networks[C]. Proceedings of the5th USENIX Symposium onOperating Systems Design and Implementation, USA: USENIX Association,2002：299-314.
[137] Borisov N. Computational Puzzles as Sybil Defenses[C]. Proceedings of the6th IEEE International Conference on Peer-to-Peer Computing, New York, NY,USA: ACM,2006:171-176.
[138] Varun T C, Kacholia V, Sankararaman S, et al. Induced Churn as Shelter fromRouting-Table Poisoning[C]. Proceedings of13th Annual Network andDistributed System Security Symposium,2006.
[139] Singh, Ngan T-Wan, Druschel P, et al. Eclipse Attacks on Overlay Networks:Threats and Defenses[C]. Proceedings of25th IEEE International Conferenceon Computer Communications, Barcelona: IEEE Press,2006：161-172.
[140] Wei H, Fedak G, Cappello F. Collaborative data distribution with bittorrent forcomputational desktop grids[C]. Proceedings of the4th InternationalSymposium on Parallel and Distributed Computing, New York, NY, USA:ACM,2005：250-257.
[141] Parvez N, Williamson C, Mahanti A, et al. Analysis of bittorrent-likeprotocols for on-demand stored media streaming[C]. Proceedings of the2008ACM SIGMETRICS international conference on Measurement and modelingof computer systems, New York, NY, USA: ACM,2008：301-312.
[142] Levin, LaCurts K, Spring N, et al. Bittorrent is an auction: analyzing andimproving bittorrent's incentives[C]. Proceedings of the ACM SIGCOMM2008conference on Data communication, New York, NY, USA: ACM,2008：243-254.
[143] Massoulié L, Vojnovi′c M. Coupon Replication Systems[C]. Proceedings ofthe2005ACM SIGMETRICS international conference on Measurement andmodeling of computer systems, New York, NY, USA: ACM,2005：2-13.
[144]史建焘，张宏莉，方滨兴. BitTorrent假块污染攻击的对抗方法研究[J].计算机学报,2011,34（1）：15-24.
[145] BitComet[EB/OL][2011-05-12]. http://www.bitcomet.com/index-zh-cn.php
[146] Bitspirit[EB/OL][2011-05-12]. http://www.bitspirit.cc