Learning-based attacks in Cyber-Physical Systems: Exploration, Detection, and Control Cost trade-offs

Abstract

We study the problem of learning-based attacks in linear systems, where the communication channel between the controller and the plant can be hijacked by a malicious attacker. We assume the attacker learns the dynamics of the system from observations, then overrides the controller's actuation signal, while mimicking legitimate operation by providing fictitious sensor readings to the controller. On the other hand, the controller is on a lookout to detect the presence of the attacker and tries to enhance the detection performance by carefully crafting its control signals. We study the trade-offs between the information acquired by the attacker from observations, the detection capabilities of the controller, and the control cost. Specifically, we provide tight upper and lower bounds on the expected $\epsilon$-deception time, namely the time required by the controller to make a decision regarding the presence of an attacker with confidence at least $(1-\epsilon \log (1/\epsilon ))$. We then show a probabilistic lower bound on the time that must be spent by the attacker learning the system, in order for the controller to have a given expected $\epsilon$-deception time. We show that this bound is also order optimal, in the sense that if the attacker satisfies it, then there exists a learning algorithm with the given order expected deception time. Finally, we show a lower bound on the expected energy expenditure required to guarantee detection with confidence at least $1-\epsilon \log (1/\epsilon )$.

arXiv commentTo appear in L4DC 2021. First two authors contributed equally

References in corpus (10)

• Near optimal finite time identification of arbitrary linear dynamical systems
• Adversarial Attacks on Stochastic Bandits
• Policy Poisoning in Batch Reinforcement Learning and Control
• Adaptive Reward-Poisoning Attacks against Reinforcement Learning
• Actively Learning Gaussian Process Dynamics
• Safe Multi-Agent Interaction through Robust Control Barrier Functions with Learned Uncertainties
• An Optimal Control View of Adversarial Machine Learning
• Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments
• Preventing Imitation Learning with Adversarial Policy Ensembles
• Adversarial Attacks on Optimization based Planners

Cited by in corpus (1)

• Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning