Learning Patterns from Unix Process Execution Traces for Intrusion Detection

Wenke Lee, Salvatore J. Stolfo, and Philip K. Chan

In this paper we describe our preliminary experiments to extend the work pioneered by Forrest (see Forrest et al. 1996) on learning the (normal abnormal) patterns of Unix processes. These patterns can be used to identify misuses of and intrusions in Unix systems. We formulated machine learning tasks on operating system call sequences of normal and abnormal (intrusion) executions of the Unix sendmail program. We show that our methods can accurately distinguish all abnormal executions of sendmail from the normal ones provided in a set of test traces. These preliminary results indicate that machine learning can play an important role by generalizing stored sequence information to perhaps provide broader intrusion detection services. The experiments also reveal some interesting and challenging problems for future research.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.