Incorporating Temporal Constraints in the Planning Task of a Hybrid Intelligent IDS

Abstract

Accurate and swift responses are crucial to Intrusion Detection Systems (IDSs), especially if automatic abortion mechanisms are running. In keeping with this idea, this work presents an extension of a Hybrid Intelligent IDS characterized by incorporating temporal control to facilitate real-time processing. The hybrid intelligent -IDS has been conceived as a Hybrid Artificial Intelligent System to perform Intrusion Detection in dynamic computer networks. It combines Artificial Neural Networks and Case-based Reasoning within a multiagent system, in order to develop a more efficient computer network security architecture. Although this temporal issue was taken into account in the initial formulation of this hybrid IDS, in this upgraded version, temporal restrictions are imposed in order to perform real/execution time processing. Experimental results are presented which validate the performance of this upgraded version.