Web intrusion detection using a graph-based sequence learning algorithm
Document Type
Conference Proceeding
Publication Date
12-1-2008
Abstract
Web Intrusion Detection System (IDS) plays a very important role on the information security. In this paper, we propose a web intrusion detection system based on the extended GSLA algorithm [1]. The proposed system uses the GSLA scheme to create a weighted diagraph model. In this model, the weight and anomaly score thresholds are introduced. The anomaly score of each session is based on the ratio of the number of abnormal links and the session length. The state of each link in the graph is marked as normal, suspended, or abnormal by comparing its weight with the threshold. We apply it to the log files from a UNIX web server and simulate the attack traffics. We also develop a web IDS interface to visualize the detection process and the diagnosis results.
Recommended Citation
Dong, Y. and Wu, B., "Web intrusion detection using a graph-based sequence learning algorithm" (2008). College of Health, Science, and Technology. 992.
https://digitalcommons.uncfsu.edu/college_health_science_technology/992