Integration of AI with ethical hacking tools for predictive vulnerability detection

Krishnasamy, Mullaishselvi and Zolkipli, Mohamad Fadli bin (2025) Integration of AI with ethical hacking tools for predictive vulnerability detection. World Journal of Advanced Research and Reviews, 27 (1). 063-074. ISSN 2581-9615

The evolving nature of cyber threats, especially zero-day exploits, demands a shift from traditional reactive security mechanisms to proactive and predictive defense strategies. This paper explores the integration of Artificial Intelligence (AI) with ethical hacking tools to enhance predictive vulnerability detection, focusing on Snort and Maltego. By embedding machine learning algorithms into these tools, their capabilities in anomaly detection and threat intelligence are significantly enhanced. This research investigates the integration of machine learning (ML) algorithms into ethical hacking tools, Snort and Maltego to strengthen their anomaly detection and threat intelligence functionalities. This study presents AI-driven framework where supervised and unsupervised learning models are embedded into Snort for packet level anomaly detection and into Maltego for enhanced threat correlation. Applying machine learning algorithms to detect and classify threats based on data from live network traffic and threat intelligence sources. Training and evaluation methods are used to improve accuracy and reduce false alarms. Although challenges like data labelling, changing patterns, and ethical issues exist, this approach greatly strengthens early threat detection and response. This research supports the advancement of intelligent cybersecurity systems capable of proactive threat mitigation.