Abstract

The rapid digital transformation of manufacturing and logistics sectors has created unprecedented interconnectivity across global supply chains, simultaneously exposing these critical infrastructures to sophisticated cyber threats. Traditional security approaches relying on signature-based detection and rule-based methods have proven inadequate against the evolving landscape of advanced persistent threats, ransomware campaigns, and state-sponsored attacks targeting operational technology environments. This paper examines how artificial intelligence-driven threat intelligence frameworks can enable real-time detection and situational awareness of cyber-attacks in manufacturing and logistics ecosystems. Through comprehensive analysis of current threat landscapes, machine learning methodologies, and operational deployment considerations, this study presents a structured framework for integrating AI capabilities across supply chain networks. The research demonstrates that AI-enhanced detection systems, incorporating anomaly detection algorithms, behavioral analysis, and predictive threat identification, can achieve detection accuracies exceeding 90% while significantly reducing mean time to detection. The findings underscore the critical importance of multi-layered AI integration spanning network telemetry analysis, operational technology sensor monitoring, and cross-organizational threat correlation for securing modern supply chain infrastructures against an increasingly hostile cyber environment.