Cyber-Physical Systems (CPS) are vital of critical infrastructure such as energy, transportation, healthcare, and manufacturing. Increasingly, however, these systems are the target of sophisticated cyber threats, with dire economic and operational implications. The CPS security literature mainly covers theory models and technology-specific security and control measures, but known techniques have low implementation/efficiency/robustness. To address these gaps, in this paper we propose a generalizable, cost-effective, and AI-enabled adaptive security framework by coupling a real-time threat monitoring system with a blockchain-based security and machine learning-enabled intrusion detection model. Real-world attack scenarios, cost-benefit analysis and a supply-chain risk mitigation strategy contribute to improving resilience against ever-evolving cyber threats. The results showcase that the framework enhances cyber resilience, scalability, and adaptability in CPS environments, providing appropriate protection for critical infrastructure. The research provides a field in the making practical, scalable, and economically viable cybersecurity solution to achieve better preparedness for cyberattacks.
Chinthamu et al. (Tue,) studied this question.