期刊文献+

一种基于信任/不信任的信誉攻击防御策略及稳定性分析 预览

A Trust-Distrust Based Reputation Attacks Defending Strategy and Its Stability Analysis
在线阅读 下载PDF
收藏 分享 导出
摘要 虽然各电子商务企业采用多种信誉评价机制解决消费者对卖方或平台的信任问题,但是信誉评价系统仍然频繁地遭受各种攻击.这些攻击致使卖方的信誉排名和推荐排名被操控,大量诚实消费者被误导而购买了质量较差的商品.有研究者提出综合考虑消费者之间的信任和不信任信息可以使消费者更好地抵御信誉攻击.然而,现有工作存在“信任或不信任信息融合不足”以及“使用一组顾问评价所有卖方”等局限性,因此导致卖方信誉评价的针对性和准确性较差.提出了一种新的防御策略——T&D,它综合考虑了消费者的可信和不可信2个方面.此外,该策略为消费者设置了白名单(存储若干个最信任的评价者)和黑名单(存储若干个最不信任的评价者).利用黑名单净化白名单,诚实消费者可以找到更可信的评价者并依据这些评价者的评分和诚实消费者自身的经历准确评估每个卖方的信誉值.模拟实验结果显示:该策略在评估准确性和稳定性方面明显优于现有防御策略. Though electronic commerce companies adopt multifarious reputation evaluation mechanisms to guarantee trust between customers and sellers(or customers and platforms),these reputation evaluation systems are still frequently attacked.These attacks have led the reputation ranking and recommendation rankings of sellers to be manipulated.Therefore,large numbers of honest consumers are misled to purchase low quality products.It has been mentioned that overall consideration of trust and distrust information can improve customers ability in defensing against reputation attacks.However,existing works have limitations such as“the trust information and distrust information are less fused”,“one advisor list is used in evaluating all sellers”,which leads to the lack of pertinence and inaccuracy of sellers reputation evaluation.We propose a new defensing strategy called T&D.This strategy considers the trustworthy facet as well as the untrustworthy facet of customers.In addition,this strategy offers a whitelist(which stores several most trustworthy reviewers)and a blacklist(which stores several most untrustworthy reviewers)for customers.Based on the whitelist that is purified using the blacklist,honest customers can find the most trustworthy buyers and evaluate the candidate sellers according to its own experience and ratings of these trustworthy reviewers.Simulated experimental results show that our proposed strategy significantly outperforms state-of-the-art baselines in evaluation accuracy and stability.
作者 马海燕 梁永全 纪淑娟 李达 Ma Haiyan;Liang Yongquan;Ji Shujuan;Li Da(College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, Shandong 266590;Shandong Provincial Key Laboratory of Wisdom Mine Information Technology (Shandong University of Science and Technology), Qingdao, Shandong 266590)
出处 《计算机研究与发展》 CSCD 北大核心 2018年第12期2685-2702,共18页 Journal of Computer Research and Development
基金 国家自然科学基金项目(71772107,71403151,61502281,61433012,91746104) 国家重点研发计划基金项目(2017YFC0804406,2018YFC0831002) 山东省自然科学基金项目(ZR2013FM023,ZR2014FP011,ZR2018BF013) 教育部人文社会科学基金项目(18YJAZH136) 山东省重点研发计划项目(2018GGX101045).
关键词 信誉系统 攻击 防御策略 信任 黑名单 白名单 reputation system attack defense strategy trust blacklist whitelist
作者简介 Ma Haiyan , born in 1990. Received his BS and MS degrees from Shandong University of Science and Technology, Shandong, China. His main research interests include artificial intelligence and intelligent business information processing;Liang Yongquan , born in 1967. Professor of the College of Computer Science and Engineering in Shandong University of Science and Technology. Received his PhD degree from the Institute of Computing Technology, Chinese Academy of Sciences. Director of Chinese Association for Artificial Intelligence, senior member of CCF, executive director of Shandong Province Computer Society, vice president of Qingdao Computer Society. His main research in-terests include distributed artificial intelli-gence, data mining, machine learning and multimedia information intelligent processing (lyq@sdust.edu.cn);Ji Shujuan , born in 1977. Associate professor of the College of Computer Science and Engineering in Shandong University of Science and Technology. Received her BS, MS and PhD degrees in computer software and theory from Shandong University of Science and Technology, Qingdao, China. Her main research interests include artificial intelligence and intelligent business informa-tion processing.通信作者 :纪淑娟(jsjsuzie@sina.com);Li Da , born in 1993. Master candidate of Shandong University of Science and Tech-nology. Received his bachelor degree from Qingdao University of Science and Tech-nology, Shandong, China in 2016. His main research interests include artificial intelligence and intelligent business infor-mation processing (893871549@qq.com).
  • 相关文献

参考文献1

二级参考文献19

  • 1Du Ruizhong, Tian Junfeng, Wang Zixian, et al. A trust model of P2P network based on reputation and risk[C] // Proc of the 2009 WRI World Congress on Software Engineering. Piscataway, NJ: IEEE, 2009: 382-386. 被引量:1
  • 2Wan K Y, Alagar V. A context-aware trust model for service oriented multi agent systems [C] //Proc of the 1st Int Workshop on Quality obService Concerns in Service Oriented Architectures. Piscataway, NJ : IEEE, 2011:362-372. 被引量:1
  • 3Yu B, Singh M P. An evidential model of distributed reputation management [C] //Proc of the 1st Int Joint Con on Autonomous Agents and Multi-Agents Systems. New York: ACM, 2002: 294-301. 被引量:1
  • 4Swamynathan G, Zhao B Y, Kevin C A, et al. Globally decoupied reputations for large distributed networks [J]. Advances in Multimedia, 2007, 2007 (1): 12-25. 被引量:1
  • 5Sharer G. A Mathematical Theory of Evidence [M]. Princeston, NJ: Princeton University Press, 1976:10-28. 被引量:1
  • 6Josang A, Pope S. Semantic constraints for trust transitivity [C] //Proc of the 2nd Asia Pacific Conf on Conceptual Modeling. New York: ACM. '2005:59-68. 被引量:1
  • 7Josang A, Gray E, Kinateder M. Analysing Topologies of Transitive Trust[R/OL].//Proc of the Workshop of Formal Aspecls of Security and Trust. 2003. [2012-01-06]. ftp:// ftp. informatik, uni stuttgart, de/pub/library/ncstrl, ustuttgart fi/INPROC-2003 19/INPROC 2003 19. pdf. 被引量:1
  • 8Zhang Mingwu, Yang Bo, Yu Yong. A distributed trust model based on DS evidence theory [J].Journal of Wuhan University: Natural Science Edition, 2009, 55(1): 41-44. 被引量:1
  • 9Josang A, Bhuiyan T, Xu Y. All analysis of trust transitivity taking base rate into account [C] //Proe of the 6th Int Conf on Ubiquitous Intelligence and Computing. Piscataway. NJ: IEEE, 2009:34-39. 被引量:1
  • 10Josang A, Marsh S, Pope S. Exploring different types of trust propagation [C] //Proc of the 4th Int Conf on Trust Management. Berlin: Springer, 2006:179-192. 被引量:1

共引文献3

投稿分析

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈