AI-Enhanced Network Forensic Techniques for Cybercrime Investigation Using the Gray Wolf Adaptive Forensic Anomaly Detection Algorithm (GADFADA)

The growth of cybercrime indicates a need for advancing forensic techniques to improve detection and prevention capabilities. This paper describes an AI-enhanced Network Forensics Framework where the Gray Wolf Adaptive Forensic Anomaly Detection Algorithm (GADFADA), a novel method for adaptive and precise anomaly detection in network traffic, is integrated. The novelty of this algorithm relies on the effective combination of the gray wolf optimization techniques and the deep learning techniques for anomaly detection, which makes the algorithm highly adaptive to evolving threats while maintaining the pure detection accuracy of the network. We found a highly successful integration of optimization techniques with anomaly detection from deep learning to identify irregularities effortlessly by being inspired by gray wolves' social structure and hunting techniques. Experimental results show that GADFADA better outperforms traditional methods, with an accuracy of 96.5, precision of 95.8, recall of 94.6, and an F1-score of 95.2. It further shows how the algorithm could be used to secure IoT systems or deal with massive network breaches. The focus of this work is on augmenting modern cybercrime investigations as well as digital forensic methodologies through the use of AI and adaptive algorithms.