# Robustness to Adversarial Attacks in Learning-Enabled Controllers

arXiv: https://arxiv.org/abs/2006.06861 · HTML: https://mlsanity.com/paper/2006.06861/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2020.

## Built on by (most cited first, 4 of 4)

- [Neural Network Repair with Reachability Analysis](https://mlsanity.com/paper/2108.04214/) (2021)
- [Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPS](https://mlsanity.com/paper/2102.07244/) (2021)
- [Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising](https://mlsanity.com/paper/2206.07188/) (2022)
- [Verified Compositional Neuro-Symbolic Control for Stochastic Systems with Temporal Logic Tasks](https://mlsanity.com/paper/2311.10863/) (2023)

## Abstract (arXiv)

Learning-enabled controllers used in cyber-physical systems (CPS) are known to be susceptible to adversarial attacks. Such attacks manifest as perturbations to the states generated by the controller's environment in response to its actions. We consider state perturbations that encompass a wide variety of adversarial attacks and describe an attack scheme for discovering adversarial states. To be useful, these attacks need to be natural, yielding states in which the controller can be reasonably expected to generate a meaningful response. We consider shield-based defenses as a means to improve controller robustness in the face of such perturbations. Our defense strategy allows us to treat the controller and environment as black-boxes with unknown dynamics. We provide a two-stage approach to construct this defense and show its effectiveness through a range of experiments on realistic continuous control domains such as the navigation control-loop of an F16 aircraft and the motion control system of humanoid robots.