Detection of server side web attacks

TitleDetection of server side web attacks
Publication TypeConference Paper
Year of Publication2010
AuthorsCorona, I, Giacinto, G
EditorCristianini, N, Shawe-Taylor, J, Diethe, T
Conference NameWorkshop on Applications of Pattern Analysis
Date Published01/09/2010
Conference LocationCumberland Lodge, London, UK
KeywordsIntrusion Detection, Multiple Classifier Systems, web security

Web servers and server-side applications constitute the key components of modern Internet services. We present a pattern recognition system to the detection of intrusion attempts that target such components. Our system is anomaly-based, i.e., we model the normal (legitimate) traffic and intrusion attempts are identified as anomalous traffic. In order to address the presence of attacks (noise) inside the training set we employ an ad-hoc outlier detection technique. This approach does not require supervision and allows us to accurately detect both known and unknown attacks against web services. 

Citation Key 1035
corona10a.pdf308.33 KB