AI-Assisted Forensic Techniques for Automated Cyber-Attack Investigation

The increasing sophistication of cyber-attacks necessitates the development of intelligent forensic investigation frameworks capable of automating digital evidence analysis and intrusion reconstruction. This study proposes an AI-assisted forensic investigation framework designed to enhance cyber-attack detection, behavioral threat attribution, and automated timeline reconstruction across heterogeneous enterprise environments. The proposed methodology integrates hybrid deep learning–based anomaly detection with behavior-aware cybersecurity analytics and explainable decision-support mechanisms. Multi-source digital evidence collected from network logs, system events, and cloud telemetry is processed using adaptive learning models to detect anomalous activity and reconstruct cyber-attack progression sequences. Experimental evaluation indicates that the proposed framework achieves a detection accuracy of 93.34%, outperforming baseline forensic models with an improvement of approximately 7.7%.

Ҳали таржима қилинмаган