# A Secure Learning Control Strategy via Dynamic Camouflaging for Unknown Dynamical Systems under Attacks

arXiv: https://arxiv.org/abs/2102.00573 · HTML: https://mlsanity.com/paper/2102.00573/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 33 references that are in the map.
- First posted on arXiv 1 Feb 2021.

## Builds on (most cited first, 10 of 10)

- [On the Sample Complexity of the Linear Quadratic Regulator](https://mlsanity.com/paper/1710.01688/) (2017)
- [Formulas for Data-driven Control: Stabilization, Optimality and Robustness](https://mlsanity.com/paper/1903.06842/) (2019)
- [Learning-based attacks in Cyber-Physical Systems: Exploration, Detection, and Control Cost trade-offs](https://mlsanity.com/paper/2011.10718/) (2020)
- [Dynamic Watermarking: Active Defense of Networked Cyber-Physical Systems](https://mlsanity.com/paper/1606.08741/) (2016)
- [Data-Injection Attacks in Stochastic Control Systems: Detectability and Performance Tradeoffs](https://mlsanity.com/paper/1704.00748/) (2017)
- [On the performance analysis of resilient networked control systems under replay attacks](https://mlsanity.com/paper/1307.2790/) (2013)
- [Covert Attacks in Cyber-Physical Control Systems](https://mlsanity.com/paper/1609.09537/) (2016)
- [Reduced-Dimensional Reinforcement Learning Control using Singular Perturbation Approximations](https://mlsanity.com/paper/2004.14501/) (2020)
- [A Moving Target Defense for Securing Cyber-Physical Systems](https://mlsanity.com/paper/1902.01423/) (2019)
- [Imposing Robust Structured Control Constraint on Reinforcement Learning of Linear Quadratic Regulator](https://mlsanity.com/paper/2011.07011/) (2020)

## Abstract (arXiv)

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.