A text based anomaly detection for web attacks

Abstract

Nowadays, there is an interaction between the web sites and users. In this interaction, user requests are sent to web servers in URL strings. Sometimes, harmful code may be embedded into those strings. Harmful code embedding is one of web attacks. User input data may be analyzed for detection of this type of attack. In this study, a text based anomaly detection method has been proposed. Proposed method uses textual properties of input data for analysis. This method that is implemented and given experimental results is particularly a new approach for web based anomaly detection. © 2011 Elsevier B.V., All rights reserved.