Anomaly-based Techniques for Web Attacks Detection

Abstract

The widespread use of the Internet comes accompanied with severe threats for web applications security. Intrusion Detection Systems (IDS) have been considered to deal with the diversity and complexity of web attacks. In this context, this work proposes an algorithm for web attack detection, exploring an anomaly-based technique: the wavelet transform. The proposed algorithm analyzes anomalies within variations on characters frequencies in web requests. Experimental results show high rates of detection without false positive occurrences.