Dynamic Updating of Profiles for an Immunity-Based Anomaly Detection System

Authors:
Takeshi Okamoto;Yoshiteru Ishida
Affiliations:
Dept. of Network Engineering, Kanagawa Institute of Technology, Kanagawa, Japan 243-0292;Dept. of Knowledge-Based Information Engineering, Toyohashi University of Technology, Tempaku, Toyohashi, Japan 441-8580
Venue:
KES '08 Proceedings of the 12th international conference on Knowledge-Based Intelligent Information and Engineering Systems, Part III
Year:
2008

Citing 4
Cited 1

CDIS: Towards a Computer Immune System for Detecting Network Intrusions

RAID '00 Proceedings of the 4th International Symposium on Recent Advances in Intrusion Detection
A Sense of Self for Unix Processes

SP '96 Proceedings of the 1996 IEEE Symposium on Security and Privacy
Framework of an immunity-based anomaly detection system for user behavior

KES'07/WIRN'07 Proceedings of the 11th international conference, KES 2007 and XVII Italian workshop on neural networks conference on Knowledge-based intelligent information and engineering systems: Part III
Towards an immunity-based anomaly detection system for network traffic

KES'06 Proceedings of the 10th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part II

Evaluations for immunity-based anomaly detection with dynamic updating of profiles

Artificial Life and Robotics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Our immunity-based anomaly detection system aims to detect anomalous behavior of users on a computer. To improve the detection accuracy, we introduced the framework of dynamically updating profiles into our system. Our system enables agents to update not only self profiles, but also nonself profiles. Briefly, our system enables agents to adapt to new behavior of the original users and of others. The receiver operating characteristic (ROC) analysis of our system indicated that the updating of both profiles markedly decreased both the false alarm rate and the missed alarm rate.