Detect Insider Attacks in Industrial Cyber-physical Systems Using Multi-physical Features-based Fingerprinting

• DOI: 10.1145/3582691
• Publication Date: 2023-02-20T11:48:38Z
• Authors: Zhen Hong; Lingling Lu; Dehua Zheng; Jiahui Suo; Peng Sun; Raheem Beyah; Zhenyu Wen
• Keywords: Testbed; Cyber-physical system; Generality

ICPS software and hardware suffer from low update frequency, making it easier for insiders to bypass external defenses launch concealed destructive attacks. To address these concerns, we design a device fingerprinting method based on multi-physical features, augmenting current intrusion detection techniques in the environment. In this paper, use sorting system as an example, demonstrating that proposed technology has generality of control flow. Specifically, first formalize physical model analyze critical features. Then extract features sensor data collected testbed. Utilizing featurized data, train classifier generates fingerprints real-time production Moreover, develop differential discover stealthy insider attacks efficiently. We evaluate real-world Experiment results show detecting performance classifiers approaches 100% when number component types is small.