A network intrusion detection framework on sparse deep denoising auto-encoder for dimensionality reduction

Abstract

AbstractIn today's internet-driven world, a multitude of attacks occurs daily, propelled by a vast user base. The effective detection of these numerous attacks is a growing area of research, primarily accomplished through intrusion detection systems (IDS). IDS are vital for monitoring network traffic to identify malicious activities, such as Denial of Service, Probe, Remote-to-Local, and User-to-Root attacks. Our research focused on evaluating different auto-encoders for enhancing network intrusion detection. The proposed method sparse deep denoising auto-encoder approach produces the dimensionality reduction used to predict and classify attacks in datasets. With the most records among the datasets by training the auto-encoder on normal network data, this utilized reconstruction error as an indicator of anomalies. We tested our approach using standard datasets like KDDCup99, NSL-KDD, UNSW-NB15, and NMITIDS. Remarkably, our sparse deep denoising auto-encoder achieved an accuracy of over 96% based solely on reconstruction error. The primary aim of this work is to improve intrusion detection by achieving higher detection accuracy compared to existing methods.