An Attack Detection Mechanism Based on a Distributed Hierarchical Multi-agent Architecture for Protecting Databases

Abstract

This paper presents an innovative approach to detect and classify SQL injection attacks. The existing approaches are centralized while this proposal is based on a distributed hierarchical architecture to provide a robust and dynamic strategy. The strategy for the classification and detection of SQL injection attacks uses a combination based on detection by anomalies and misuses. The detection by anomaly uses a case-based reasoning mechanism incorporating a mixture of neural networks. The approach has been tested and the results are presented in this paper.