Protection of an Intrusion Detection Engine with Watermarking in Ad Hoc Networks

In this paper we present an intrusion detection enginecomprised of two main elements; firstly, a neural networkfor the actual detection task and secondly watermarking techniques for protecting the related information thatmust be exchanged between nodes. In particular, we exploit information visualization and machine learning techniques in order to achieve efficient and effective intrusiondetection. In order to avoid possible modification or alteration of the maps produced by the intrusion detectionengine, we focus on safeguarding and authenticating themusing a novel embedded watermarking method. Previously, we had shown promising results in the intrusiondetection task using this system. This paper focuses onthe watermarking technique and gives a detailed exposition that includes an experimental evaluation of its quality