Visible to the public A Secure Learning Control Strategy via Dynamic Camouflaging for Unknown Dynamical Systems under Attacks

TitleA Secure Learning Control Strategy via Dynamic Camouflaging for Unknown Dynamical Systems under Attacks
Publication TypeConference Paper
Year of Publication2021
AuthorsMukherjee, Sayak, Adetola, Veronica
Conference Name2021 IEEE Conference on Control Technology and Applications (CCTA)
Keywordsattack-resilient learning control., composability, covert attacks, cps security, cyber physical systems, dynamic systems, Dynamical Systems, Heuristic algorithms, Metrics, Nonlinear dynamical systems, Numerical models, Power system dynamics, Predictive Metrics, pubcrawl, Regulators, reinforcement learning, resilience, Resiliency, security, System Dynamics
Abstract

This paper presents a secure reinforcement learning (RL) based control method for unknown linear time-invariant cyber-physical systems (CPSs) that are subjected to compositional attacks such as eavesdropping and covert attack. We consider the attack scenario where the attacker learns about the dynamic model during the exploration phase of the learning conducted by the designer to learn a linear quadratic regulator (LQR), and thereafter, use such information to conduct a covert attack on the dynamic system, which we refer to as doubly learning-based control and attack (DLCA) framework. We propose a dynamic camouflaging based attack-resilient reinforcement learning (ARRL) algorithm which can learn the desired optimal controller for the dynamic system, and at the same time, can inject sufficient misinformation in the estimation of system dynamics by the attacker. The algorithm is accompanied by theoretical guarantees and extensive numerical experiments on a consensus multi-agent system and on a benchmark power grid model.

DOI10.1109/CCTA48906.2021.9659093
Citation Keymukherjee_secure_2021