Secure Planning Against Stealthy Attacks via Model-Free Reinforcement Learning
This addresses security for robotic systems against stealthy attacks, but it is incremental as it applies known RL methods to a specific security scenario.
The paper tackles the problem of security-aware planning for robots in unknown stochastic environments under stealthy actuator attacks, modeling it as a stochastic game with linear temporal logic objectives and solving it using model-free reinforcement learning, with evaluation on two robotic case studies.
We consider the problem of security-aware planning in an unknown stochastic environment, in the presence of attacks on control signals (i.e., actuators) of the robot. We model the attacker as an agent who has the full knowledge of the controller as well as the employed intrusion-detection system and who wants to prevent the controller from performing tasks while staying stealthy. We formulate the problem as a stochastic game between the attacker and the controller and present an approach to express the objective of such an agent and the controller as a combined linear temporal logic (LTL) formula. We then show that the planning problem, described formally as the problem of satisfying an LTL formula in a stochastic game, can be solved via model-free reinforcement learning when the environment is completely unknown. Finally, we illustrate and evaluate our methods on two robotic planning case studies.