Fuzzy Embedding to Detect Intrusion in Software-Defined Networks

Software-defined networks (SDN) play a vital role in modern networking systems. In recent years, several machine learning-based approaches have been proposed to detect the intrusions attacking SDN. They are all based on fixed embedding methods that try to map the original data into a constant setting of a latent space. In this paper we propose a novel fuzzy embedding method that improve the performance of the intrusion detection systems in SDN. We evaluate our proposal using real-world dataset and show the empirical improvement.