Internet and Web Applications and Services, International Conference on (2009)
May 24, 2009 to May 28, 2009
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICIW.2009.67
Security of web servers has become a sensitive subject today. Prediction of normal and abnormal request is problematic due to large number of false alarms in many anomaly based Intrusion Detection Systems (IDS). SS-IDS derives automatically the parameter profiles from the analyzed data thereby generating the Statistical Signatures. Statistical Signatures are based on modeling of normal requests and their distribution value without explicit intervention. Several attributes are used to calculate the behavior of the legitimate request on the web server. SS-IDS is best suited for the newly installed web servers which doesn’t have large number of requests in the data set to train the IDS and can be used on top of currently used signature based IDS like SNORT. Experiments conducted on real data sets have shown high accuracy up to 99.98% for predicting valid request as valid and false positive rate ranges from 3.82-7.84%.
Chedy Raïssi, Pascal Poncelet, Gerard Dray, Payas Gupta, Johan Brissaud, "SS-IDS: Statistical Signature Based IDS", Internet and Web Applications and Services, International Conference on, vol. 00, no. , pp. 407-412, 2009, doi:10.1109/ICIW.2009.67