Intrusion Detection with deep learning: A literature review

As technology continues to grow and becomes increasingly integral to education, institutions and universities worldwide are making substantial investments in e-learning platforms to help and enhance their students' learning and performance experiences. Recently, Internet users have witnessed an increase in vulnerability to cyber-attacks due to the diversity and prevalence of scams across the web. This threat is phishing attacks and malware through stealing users' personal and financial information, unauthorized access to their online accounts, and tarnishing their reputation across the network. This is due to the exploitation of vulnerabilities in systems and lack of security awareness among users. In recent years, have seen the emergence of IDS systems leveraging machine learning (ML) and deep learning (DL) technologies as promising solutions for efficiently detecting network intrusions. In this study, we present a literature review of deep learning algorithms for intrusion detection. A brief demonstration of some DL techniques is provided. Then we discuss how each of the DL methods is used for intrusion detection. We cover a broad array of attack types including malware. We also present a comparison with the efficiency of methods, field implementation to demonstrate network safeguard enhancement technological advantages. Overall, the objective of this paper is to give an orientation and recommendations for researchers and also experts in the field of cyber-security, especially in the context of deep learning.