Resilient-Learning Control of Cyber-Physical Systems Against Mixed-Type Network Attacks

This article develops a resilient-learning control strategy for a kind of cyber-physical system to mitigate the influence of a mixed-type of network attacks. Such an attack is composed of a false-data-injection attack and a replay attack, which can be represented comprehensively by using Markov jump signals. Note that the involved attacks are assumed to be uncertain, which requires a three-layer neural network to learn them. Based on attack approximations as the output from the neural network, a resilient and efficient controller is designed to defend against the mixed-type of network attacks, in which several adaptive laws are proposed to estimate the involved neural network weights. Under the designed controller, the ultimate boundness and asymptotical stability are discussed. Finally, a practical vertical taking-off and landing helicopter model is proposed to verify the developed controller.