AI-Driven Cyber Threat Prediction for Secure Supply Chains

K. Mounika1, Ammapalli Bhargavi Sai2, Bachhu Harika3, Greeshma Peram4,Potli Karthik Kumar Reddy5
1Assistant Professor, Dept of Information Technology, SV College of Engineering, Tirupathi, India
2B. Tech, Dept of Information Technology, SV College of Engineering, Tirupathi, India.
3B. Tech, Dept of Information Technology, SV College of Engineering, Tirupathi, India.
4B. Tech, Dept of Information Technology, SV College of Engineering, Tirupathi, India.
5B. Tech, Dept of Information Technology, SV College of Engineering. Tirupathi, India.
Email: 1mounikareddy.k@svce.edu.in,2ammapallibhargavi20@gmail.com, 3harikabachhu19@gmail.com,
4greesh63042@gmail.com, 5karthikreddy2902@gmail.com
Corresponding Author *: K. Mounika

Abstract-The increasing digital interconnectivity of modern supply chains has significantly expanded their exposure to cyber threats, where a compromise at asingle node can propagate across multiple organizational partners. Conventional signature-based intrusion detection systems are reactive and insufficient for identifying emerging or behaviorally subtle attacks in such distributed environments. This paper presents an AI-driven cyber threat prediction framework that integrates Cyber Threat Intelligence aligned behavioral features with a machine learning based Network Intrusion Detection System for real time multi-class attack classification. The model is trained on a KDD-based dataset and categorizes network traffic into Normal, Denial of Service (DoS), Probe, Remote to Local (R2L), and User to Root (U2R) classes. Multiple algorithms were evaluated, with Random Forest achieving the highest performance, attaining 94% accuracy, 0.93 precision, 0.91 recall, and an F1-score of 0.92. The trained model was deployed using a Flask-based web application within a containerized environment,achieving prediction latency below 120ms. Experimental results demonstrate strong detection of high-volume attacks and acceptableperformance for low frequency intrusions, confirming the feasibility of deploying AI-driven predictive security mechanismsfor proactive risk monitoring in distributed supply chain networks. Keywords- Cyber Threat Intelligence, Intrusion Detection System, Machine Learning, Supply Chain Security, Random Forest, Real-Time Threat Prediction