INTELLIGENT FORENSICS: GENDER IDENTIFICATION OF HUMAN CYBER ATTACKERS USING ML

Abstract

As cybercrime continues to escalate globally, digital forensics faces the challenge of not only attributing attacks to systems but also profiling the human adversaries behind them. One emerging dimension is gender attribution, which can provide critical investigative leads in criminal profiling, social engineering detection, and insider threat analysis. This paper introduces a machine learning (ML)-based forensic framework designed to identify the gender of human cyber attackers by analyzing behavioral, linguistic, and keystroke dynamics in digital footprints. The proposed system leverages supervised ML classifiers to enhance profiling accuracy while reducing false attribution rates. Experimental evaluation using benchmark forensic datasets demonstrates that the framework can achieve over 90% accuracy, outperforming existing methods. The findings highlight the potential of ML-driven gender attribution as a complementary tool in intelligent digital forensics