A New Approach for Adaptive Intrusion Detection

Adaptability is a relevant feature for an Intrusion Detection System (IDS). It enables the IDS to adjust itself in a dynamic changing environment by practicing autonomous learning of new attacks and normal behavior patterns. Therefore, the IDS will be able to ensure its sustainability and effectiveness in computing environments which are becoming increasingly evolutionary and dynamic. However, the adaptability remains a messing functionality in the design of existing IDSs and the research works offer a limited and constrained adaptability. This paper proposes a new approach for IDS adaptability by integrating a Simple COnnectionist Evolving System (SECOS) and a Winner-Takes-All (WTA) hierarchy of XCS (eXtended Classifier System). This integration puts in relief an adaptive hybrid intrusion detection core that plants the adaptability as an intrinsic and native functionality in the IDS.