Learning Temporal Regularities of User Behavior for Anomaly Detection
Fast expansion of inexpensive computers and computer networks has dramatically increased number of computer security incidents during last years. While quite many computer systems are still vulnerable to numerous attacks, intrusion detection has become vitally important as a response to constantly increasing number of threats. In this paper we discuss an approach to discover temporal and sequential regularities in user behavior. We present an algorithm that allows creating and maintaining user profiles relying not only on sequential information but taking into account temporal features, such as events’ lengths and possible temporal relations between them. The constructed profiles represent peculiarities of users’ behavior and used to decide whether a behavior of a certain user is normal or abnormal.
KeywordsNetwork Security Intrusion Detection Anomaly Detection Online Learning User Profiling User Recognition
Unable to display preview. Download preview PDF.
- 1.Lunt, T. and Tamaru, A. and Gilham, F. and Jagannathan, R. and Neumann, P. and Javitz, H. and Valdes, A. and Garvey, T.: A Real-Time Intrusion detection Expert System (IDES) — Final Technical Report. Computer Science Laboratory, SRI International, Technical (1992)Google Scholar
- 2.Smaha, S.: Tools for Misuse Detection. ISSA’93, Crystal City, VA (1993)Google Scholar
- 3.Seleznyov, A. and Puuronen, S.: Anomaly Intrusion Detection Systems: Handling Temporal Relations between Events. 2nd International Workshop on Recent Advances in Intrusion Detection, Lafayette, Indiana, USA (1999)Google Scholar
- 4.Seleznyov, A. and Puuronen, S.: HIDSUR: A Hybrid Intrusion Detection System based on Real-time User Recognition. 11th International Workshop on Database and Expert Systems Applications, Greenwich-London, England (2000)Google Scholar