Noise-Robust Multilayer Perceptron Architecture for Distributed Denial of Service Attack Detection

Distributed Denial of Service (DDoS) attacks are one the most challenging security threats, since a single victim is attacked by several compromised malicious nodes. As consequence, legitimate end users can be prevented to access network resources. This letter proposes noise-robust multilayer perceptron (MLP) architecture for DDoS attack detection trained with corrupted data. In proposed approach, average value common features among dataset instances iteratively filtered out applying Higher Order Singular Value Decomposition (HOSVD) based techniques. The effectiveness validated through comparison state-of-the-art methods.