Advanced In-Depth Literature Review on Intrusion Detection Systems

Abstract

As cyber protective systems become more advanced, they rely on constant intrusion monitoring and tackling access, attacks, and associated renewing dangers to disguise malicious activities within the network. Modern cybersecurity designs would not be complete without intrusion detection systems (IDS), which monitor networks for suspicious activity and new threats. Three groups are examined in this work regarding IDS transformation: signature-based detection, anomaly-based detection, and hybrid models involving AI and ML. Federalized learning, blockchain integration, and zero-trust architectures are some of the new areas of research that are being thoroughly discussed. Other topics covered include the underlying methodologies, the integration of advanced AI/ML techniques, technical challenges like scalability and encrypted traffic analysis, and emerging trends in the field. The review draws upon diverse sources from IEEE, ACM, Springer, IOPscience, and ScienceDirect.