A multi-model approach to the detection of web-based attacks

Web-based vulnerabilities represent a substantial portion of the security exposures of computer networks. In order to detect known web-based attacks, misuse detection systems are equipped with a large number of signatures. Unfortunately, it is difficult to keep up with the daily disclosure of web-related vulnerabilities, and, in addition, vulnerabilities may be introduced by installation-specific web-based applications. Therefore, misuse detection systems should be complemented with anomaly detection systems. This paper presents an intrusion detection system that uses a number of different anomaly detection techniques to detect attacks against web servers and web-based applications. The system analyzes client queries that reference serverside programs and creates models for a wide-range of different features of these queries. Examples of such features are access patterns of server-side programs or values of individual parameters in their invocation. In particular, the use of application-specific characterization of the invocation parameters allows the system to perform focused analysis and produce a reduced number of false positives. The system derives automatically the parameter profiles associated with web applications (e.g., length and structure of parameters) and relationships between queries (e.g., access times and sequences) from the analyzed data. Therefore, it can be deployed in very different application environments without having to perform time-consuming tuning and