Toward Enhancing Cyber-Physical System Security with System Unidentifiability

A substantial amount of research has shown that most attacks on cyber- physical systems rely on knowledge of system models, where the models can be obtained using identification methods. Hence, achieving unidentifiability is an attractive way for the security of systems. This paper focuses on the unidentifiability of systems and designs a controller against the attacks relying on identification. The key insight is that we propose a quantitative evaluation to measure the unidentifiability of the system. This evaluation can be taken as a criterion for evaluating the security of the system. Different from the existing research, the evaluation gives the exact number of unidentifiable parameters in the system. Moreover, we give the necessary and sufficient condition for each parameter to be unidentifiable. Finally, we design a controller based on this evaluation to maximize the number of unidentifiable parameters. Simulation demonstrates the effectiveness of our algorithm. Copyright (c) 2023 The Authors.