计算机应用 ›› 2015, Vol. 35 ›› Issue (4): 985-990.DOI: 10.11772/j.issn.1001-9081.2015.04.0985

• 信息安全 • 上一篇    下一篇

基于蚁群算法的加强型可抵御攻击信任管理模型

汪灏1,2, 张玉清2   

  1. 1. 武汉大学 计算机学院, 武汉 430072;
    2. 中国科学院大学 国家计算机网络入侵防范中心, 北京 101408
  • 收稿日期:2014-12-07 修回日期:2015-01-11 出版日期:2015-04-10 发布日期:2015-04-08
  • 通讯作者: 汪灏
  • 作者简介:汪灏(1984-),男,湖北应城人,博士研究生,主要研究方向:信任管理、计算机系统安全; 张玉清(1966-),男,陕西宝鸡人,教授,博士,主要研究方向:手机与移动互联网安全、网络攻防与系统攻防、密码学、无线通信网络与安全。
  • 基金资助:

    国家自然科学基金资助项目(61272481);北京市自然科学基金资助项目(4122089)。

Enhanced attack-resistible ant-based trust and reputation model

WANG Hao1,2, ZHANG Yuqing2   

  1. 1. School of Computer, Wuhan University, Wuhan Hubei 430072, China;
    2. National Computer Network Intrusion Protection Center, University of Chinese Academy of Sciences, Beijing 101408, China
  • Received:2014-12-07 Revised:2015-01-11 Online:2015-04-10 Published:2015-04-08

摘要:

通过将网络节点推荐行为分析和网络恶意节点密度的自适应机制纳入信誉度评价过程,提出了基于蚁群算法的加强型可抵御攻击信任管理模型——EAraTRM,以解决传统信任模型因较少考虑节点的推荐欺骗行为而导致容易在恶意节点的合谋攻击影响下失准的问题。在对比研究中发现,EAraTRM可以在网络中恶意节点密度达到90%,其他传统信任模型已经失效的情况下,仍保持较高的正确性。实验结果表明,EAraTRM能提高节点评价其他节点信誉度时的精度,并降低整个网络中恶意节点间进行合谋攻击的成功率。

关键词: 信任管理, 蚁群算法, 异常检测, 信誉度评估

Abstract:

Traditional trust and reputation models do not pay enough attention to nodes'deceit in recommendation, so their reputation evaluation may be affected by malicious nodes' collusion. A trust and reputation model named Enhanced Attack Resistible Ant-based Trust and Reputation Model (EAraTRM) was proposed, which is based on ant colony algorithm. Node recommendation behaviors analysis and adaptive mechanism to malicious nodes density were added into reputation evaluation of EAraTRM to overcome the shortage of traditional models. Simulation experiments show that EAraTRM can restrain the collusion of malicious nodes, and give more accurate reputation evaluation results, even when 90% nodes in a network are malicious and the comparison models have failed.

Key words: trust and reputation management, ant colony algorithm, anomaly detection, reputation evaluation

中图分类号: