Detecting anomalous agents in mobile agent system: a preliminary approach

ABSTRACT

Mobile agents are easy to be attacked. Although traditional security methods (authentication, encryption, etc.) can protect them from certain kinds of attacks, mobile agent can still be exploited for illegal purpose. In our approach, we propose an anomaly detection model for detecting malicious agents. We analyze mobile agent's activity by measuring its movement pattern and residence time on hosts in this preliminary approach. We classify the normal agent tracks and predict the next agent's hop. We do experiments to test the prediction algorithm and analyze the results. Further on, our research will focus on detecting abnormal execution of agent's code.

REFERENCES

• 1: Kristian Schelderup , Jon Ølnes, Mobile Agent Security - Issues and Directions, Proceedings of the 6th International Conference on Intelligence and Services in Networks: Paving the Way for an Open Service Market, p.155-167, April 27-29, 1999
• 2: Roland B., D. Kesdogan, P. Reichl, "How to increase security in mobile networks by anomaly detection"
• 3: Yongguang Zhang , Wenke Lee, Intrusion detection in wireless ad-hoc networks, Proceedings of the 6th annual international conference on Mobile computing and networking, p.275-283, August 06-11, 2000, Boston, Massachusetts, United States [doi>10.1145/345910.345958]
• 4: T. Lunt, A. Tamaru, F. Gillman, "A real time intrusion detection expert system (IDES)", Technical report, Computer Science Lab., SRI international, Menlo Park, Cal. Feb. 1992
• 5: W. Lee, S. J. Stolfo, and K. W. Mok, "A data mining framework for building intrusion detection models", in proceeding of the 1999 IEEE symposium on security and privacy, May 1999
• 6: Tieyan Li. "Applying anomaly detection in mobile agent system". To appear

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.11 Distributed Artificial Intelligence
            Subjects: Multiagent systems; Intelligent agents

General Terms:
Design, Security

Keywords:
agent movement pattern, anomaly detection, mobile agent security