AI-Augmented Intrusion Detection Systems for Mitigating Advanced Persistent Threats in Cyber-Physical Manufacturing Networks

Cyber-Physical Manufacturing Networks (CPMNs) are increasingly exposed to sophisticated cyberattacks, particularly Advanced Persistent Threats (APTs), which stealthily compromise system integrity over extended periods. Conventional intrusion detection systems often struggle to identify such adaptive and stealthy threats in real time, necessitating more intelligent and dynamic security solutions. This paper explores AI-augmented intrusion detection systems designed to enhance threat detection accuracy and response efficiency within CPMNs. The study elaborates on how machine learning algorithms and deep learning models can analyse diverse network and sensor data to detect anomalous behaviours indicative of APTs. It further discusses the architecture of such AI-driven IDS frameworks, highlighting their ability to adapt to evolving attack patterns and reduce false positives. Real-world manufacturing use cases are examined to demonstrate the practical effectiveness and challenges in deployment. The findings emphasize that integrating AI with traditional IDS offers a robust defence mechanism that supports continuous monitoring and proactive mitigation, crucial for maintaining operational continuity and safety in manufacturing environments. The study concludes by outlining future directions for enhancing AI model explainability, scalability, and resilience in increasingly complex cyber-physical manufacturing landscapes.