Feature Correlation Map based Statistical Approach for Denial of Service Attacks Detection

Abstract

Denial of Service (DoS) attack has been considered as one of the most promising threats to network security that denies access to services offered by networks or servers for legitimate users. Therefore, to protect the computing resources against these attacks, DoS attack detection system is needed. The existing statistical based attack detection systems face the lacuna of crippling dimensionality and suffer from low accuracy and high false alarm. In this paper, to address this issue, a system for the detection of DoS attacks using Feature Correlation Map (FCM) based statistical approach is proposed. FCM is the process of extracting the correlative information between selected features of each record. The normal traffic profile is constructed using Hellinger Distance measure. The distance between FCM and mean of normal traffic FCMs is computed to determine if the new network traffic belongs to either normal or attack traffic. The proposed approach is tested with benchmark datasets and compared with state-of-the-art statistical attack detection systems. It is evident that the proposed approach yields promising results than the existing attack detection systems.