Improving Intrusion Detection Performance Using Rough Set Theory and Association Rule Mining
Xuren Wang, Famei He · 2006 International Conference on Hybrid Information Technology · 2006
Intrusion Detection System has some defects, such as signatures being generated manually, updating attack signatures difficultly and doing nothing in front of ultra data set. This paper presents a hybrid approaches for modeling IDS. Association rule mining and Rough set theory are combined as a hierarchical hybrid intelligent system model. The hybrid intrusion detection model combines association rule mining and rough set theory to improve detection accuracy and reduce false alarm, unreal alarm and computational complexity. Empirical results illustrate that the hybrid intrusion detection model can detect intrusion more accurately.