Conferences in Research and Practice in Information Technology
  

Online Version - Last Updated - 20 Jan 2012

 

 
Home
 

 
Procedures and Resources for Authors

 
Information and Resources for Volume Editors
 

 
Orders and Subscriptions
 

 
Published Articles

 
Upcoming Volumes
 

 
Contact Us
 

 
Useful External Links
 

 
CRPIT Site Search
 
    

Detection of Anomalies from User Profiles Generated from System Logs

Corney, M., Mohay, G. and Clark, A.

    We describe research into the identification of anomalous events and event patterns as manifested in computer system logs. Prototype software has been developed with a capability that identifies anomalous events based on usage patterns or user profiles, and alerts administrators when such events are identified. To reduce the number of false positive alerts we have investigated the use of different user profile training techniques and introduce the use of abstractions to group together applications which are related. Our results suggest that the number of false alerts that are generated is significantly reduced when a growing time window is used for user profile training and when abstraction into groups of applications is used.
Cite as: Corney, M., Mohay, G. and Clark, A. (2011). Detection of Anomalies from User Profiles Generated from System Logs. In Proc. Australasian Information Security Conference (AISC 2011) Perth, Australia. CRPIT, 116. Colin Boyd and Josef Pieprzyk Eds., ACS. 23-32
pdf (from crpit.com) pdf (local if available) BibTeX EndNote GS