Intrusion Detection by New Data Description Method

This paper presents a new approach in data description for intrusion detection based on Support Vector Data Description (SVDD). The SVDD is a well-known kernel method which tries to fit a hypersphere around the target objects and more precise boundary is depending on using proper kernel functions. In the proposed method we find a minimal hyperellipse around the normal objects to describe them. The overall experiments show prominence of our proposed method in comparison with the standard SVDD.