P2P网络中基于矢量空间的分布式信任模型  

A Distributed Trust Model Based on Vector Space in P2P Networks

作　　者：郭磊涛[1] 杨寿保[1] 王菁[1] 周金洋[1] 

机构地区：[1]中国科学技术大学计算机科学技术系,合肥230026

出　　处：《计算机研究与发展》2006年第9期1564-1570,共7页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(60273041);国家"八六三"高技术研究发展计划基金项目(2002AA104560)

摘　　要：传统安全方案已无法解决P2P网络中诸如服务欺骗和节点滥用资源的问题.基于信誉的信任系统可以抑制该类恶意行为,但容易受到节点有策略的改变服务质量和提供不诚实回馈信息的攻击.借助社会网络信任关系模型,利用“时间敏感因子”来提高信任模型检测节点行为的敏感性,通过基于矢量空间模型的推荐可信度来防止节点的串谋和诋毁攻击,从而构建了一个基于矢量空间的分布式信任模型,并基于RChain给出了该模型的分布式实现方案.模拟实验和分析表明,该模型简单有效,且具有较好的工程可行性.Peers in P2P networks share some peers may provide fake services, resources voluntarily. They may arbitrarily terminate services, and so the QoS of services are not reliable. Moreover, peers are selfinterest and rationality. Some peers always abuse resources but seldom contribute their own resources, which induces the free-riding in P2P networks. Traditional security schemes can hardly solve the fake services providing and free-ridings in P2P networks. The trust model based on reputation can restrain these kinds of malicious behaviors. However, it suffers much from strategically altering behaviors and dishonest feedbacks from malicious peers. Recurring to the trust model of society network, a distributed trust model based on vector space is proposed. This trust model uses ‘ time-sensitive factor＇ to improve the sensitiveness of detecting peers＇ behaviors, and recommendation trust based on vector space model to prevent collusion and bad-mouthing among peers. Furthermore, a distributed implementation schema based on R-Chain is proposed. Simulation and analysis show that this trust model is effective and has favorable feasibility of implementation.

关 键 词：信任模型 矢量空间模型 R-Chain 串谋诋毁 

分 类 号：TP338.8[自动化与计算机技术—计算机系统结构]