ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2014, Vol. 51 ›› Issue (10): 2308-2317.doi: 10.7544/issn1000-1239.2014.20130619

• 人工智能 • 上一篇    下一篇



  1. (河北大学网络技术研究所 河北保定 071002) (
  • 出版日期: 2014-10-01
  • 基金资助: 

A Cloud User Behavior Authentication Model Based on Multi-Partite Graphs

Tian Junfeng, Cao Xun   

  1. (Institute of Network Technology, Hebei University, Baoding, Hebei 071002)
  • Online: 2014-10-01

摘要: 云计算迅猛发展,云平台的可信性是关乎其成败的关键问题,而用户行为可信性认定是保证云平台可信的重要环节.提出一种基于多部图的云用户行为认定模型,通过行为证据层、行为多部图构建层和行为认定层3个层次来解决云服务中用户行为可信性问题;同时引入身份再认证和风险博弈来增强模型的安全性与准确性.仿真实验通过对小规模云子域用户行为的分析表明,该模型可以准确地描述云用户的正常行为,对恶意用户有较高检测率,同时能有效地区分恶意用户与风险型用户,降低误报率.

关键词: 云计算, 行为证据, 行为多部图, 可信性, 行为认定

Abstract: Cloud computing is developing rapidly, and the trustiness of cloud platform is the key issue relating to its success or failure. The authentication of the trustiness of user behavior is an important part of ensuring the credibility of cloud platform. In order to solve the problem of trustiness of cloud users’ behaviors, a cloud user behavior authentication model based on multi-partite graphs (BAM) is proposed. It includes the layer of user behavior evidence, the layer of building behavior multi-partite graphs and the layer of behavior authentication. The behavior evidence is the basis, the multi-partite graphs is the method and the behavior authentication is the purpose. In the layer of user behavior evidence, the model determines the type of evidence, collects behavior evidences and analyzes user behavior quantitatively; in the layer of building behavior multi-partite graphs, the model builds two multi-partite graphs based on the layer of behavior evidence and the knowledge of graph theory; in the layer of behavior authentication, the model builds the cloud user behavior authentication module to verify that users are trusted. Identity re-certification and risk game are introduced to enhance security and accuracy of the model. The analysis of small-scale cloud user behaviors in simulation experiments show that, the model is accurate and effective in measuring the normal behavior of cloud users and in distinguishing malicious user with the risk user, and it has higher detection ratio and lower false positive ratio.

Key words: cloud computing, behavior evidence, behavior multi-partite graphs, trustiness, behavior authentication