Minimizing false positive rate for DoS attack detection: A hybrid SDN-based approach

Abstract

Denial of Service attacks (DoS) are considered to be a major threat against today's communication networks. Recently, a novel networking paradigm that provides enhanced programming abilities has been proposed to attain an efficient control and management in future networks. In this work, we take the advantage of software-defined networking (SDN) to minimize the false positive rate of DoS attack detection systems. Our system combines flow-based and packet-based approaches to minimize the false positive rate (FPR). The experimental results conducted on NSL-KDD dataset have shown the effectiveness of our proposed approach, which successfully minimized the FPR as low as 0.3%. (C) 2020 The Korean Institute of Communications and Information Sciences (KICS).