Smart Network Forensics with Generative Adversarial Networks Leveraging Blockchain for Anomaly Detection and Immutable Audit Trails

Abstract

Analyzing the specificity of the cybersecurity domain, the problem of ensuring the security and integrity of smart networks is multifaceted. This research explores the complexity of smart network forensics and seeks to meet theses challenges through different approaches. First, to establish the subject of the investigation, the context is described, which includes factors such as ever-fluctuating network traffic and increasing threat types. Further, a thorough analysis of the literature and research work available in the field of network forensics, anomaly detection methodologies, generative adversarial networks, and blockchain technology bring new perspectives and information to the discussion. From this perspective, the proposed methodology contributes towards devising a novel concept. Drawing on the prospects of using GANs for detecting anomalies, this research investigates how GANs can be employed to add synthetic data to training sets and improve the efficiency of smart networks in detecting anomalies. Similarly, Blockchain becomes a valuable asset in creating unalterable audit trails, and providing accountability and recoverability of any examined evidence. By incorporating these state-of-the-art approaches into the proposed work, this research aims at enhancing the reliability of smart network forensics to advance more effective cybersecurity awareness and threat analysis in complex and ever-evolving networks. DOI: https://doi.org/10.52783/pst.432