iDetect: Content Based Monitoring of Complex Networks using Mobile Agents

With the evolution in computer networks over the last decade, researchers are trying to come up with efficient approaches which can help network administrator in implementing the acceptable use policy for large complex networks. In this paper we have modified An Agent Based System for Activity Monitoring on Network – ABSAMN architecture and proposed iDetect: Content Based Monitoring of Complex Network using Mobile Agents which uses the content (i.e. text, image and video) of the application for categorization purpose. iDetect is implemented in Java using Java Agent Development (JADE) framework and supports platform independence; however, the framework has been tested only on Microsoft Windows (any version) environment. We have evaluated iDetect and ABSAMN on same configuration concurrently at the university campus having four labs equipped with 60–120 number of PCs in various labs; experimental results shows that iDetect efficiently detects known/unknown illegal activities (applications/websites) running on the network as compared to ABSAMN.