Agent-oriented design for network survivability

Intelligent behavior is the selection of actions based on knowledge. The design of the fuzzy adaptive survivability tool (FAST) agents and their intelligent behavior is explained. A FAST agent uses Belief-Desire-Intention (BDI) logic as the reasoning framework to decide on desirable response plans. These decisions are both context-sensitive to take into account the changes in the network status and cost-sensitive to avoid the risk of collateral damage. A real-world scenario, which shows how the FAST agents choose desirable responses to mitigate scanning worm traffic, is also presented.

[1]  Julie A. Dickerson,et al.  Fuzzy intrusion detection , 2001, Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference (Cat. No. 01TH8569).

[2]  Wenke Lee,et al.  Integrating intrusion detection and network management , 2002, NOMS 2002. IEEE/IFIP Network Operations and Management Symposium. ' Management Solutions for the New Communications World'(Cat. No.02CH37327).

[3]  Mehdi Shajari.  Enhancing network survivability using intelligent agents , 2005 .

[4]  Michael Papasimeon,et al.  Extending the UML for designing Jack agents , 2001, Proceedings 2001 Australian Software Engineering Conference.

[5]  Eugene H. Spafford,et al.  Intrusion detection using autonomous agents , 2000, Comput. Networks.

[6]  Anand S. Rao,et al.  Modeling Rational Agents within a BDI-Architecture , 1997, KR.

[7]  李幼升,et al.  Ph , 1989 .

[8]  Ali A. Ghorbani,et al.  Using Fuzzy System to Manage False Alarms in Intrusion Detection , 2003, SEC.