Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approach
On the map: Deep reinforcement learning methods → Adversarial robustness and RL in finance
Abstract (arXiv)
Reinforcement learning (RL) for the Markov Decision Process (MDP) has emerged in many security-related applications, such as autonomous driving, financial decisions, and drone/robot algorithms. In order to improve the robustness/defense of RL systems against adversaries, studying various adversarial attacks on RL systems is very important. Most previous work considered deterministic adversarial attack strategies in MDP, which the recipient (victim) agent can defeat by reversing the deterministic attacks. In this paper, we propose a provably ``invincible'' or ``uncounterable'' type of adversarial attack on RL. The attackers apply a rate-distortion information-theoretic approach to randomly change agents' observations of the transition kernel (or other properties) so that the agent gains zero or very limited information about the ground-truth kernel (or other properties) during the training. We derive an information-theoretic lower bound on the recipient agent's reward regret and show the impact of rate-distortion attacks on state-of-the-art model-based and model-free algorithms. We also extend this notion of an information-theoretic approach to other types of adversarial attack, such as state observation attacks.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods. Builds on 16 of its 28 references that are in the map. First posted on arXiv 15 Oct 2025.
Builds on
16 of 28 references.
References · 16
- 2017Robust Adversarial Reinforcement Learningcited by 451
- 2016Safe, Multi-Agent, Reinforcement Learning for Autonomous Drivingcited by 311
- 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 154
- 2018Deep Reinforcement Learning for Page-wise Recommendationscited by 100
- 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
- 2020FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Financecited by 87
- 2020Adaptive Reward-Poisoning Attacks against Reinforcement Learningcited by 86
- 2020Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learningcited by 81
- 2019Policy Poisoning in Batch Reinforcement Learning and Controlcited by 70
- 2021Autonomous Drone Racing with Deep Reinforcement Learningcited by 60
- 2019Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signalscited by 50
- 2021Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learningcited by 29
4 more
- 2022Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attackscited by 12
- 2023Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learningcited by 10
- 2021Bayesian Risk Markov Decision Processescited by 6
- 2023Policy Resilience to Environment Poisoning Attacks on Reinforcement Learningcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Towards Optimal Adversarial Robust Reinforcement Learning with Infinity Measurement Error
- 2025State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning
- 2024Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
- 2025Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
- 2024Scale-free Adversarial Reinforcement Learning
- 2026Reward-Preserving Attacks For Robust Reinforcement Learning
- 2025Policy Disruption in Reinforcement Learning:Adversarial Attack with Large Language Models and Critical State Identification
- 2025Adversarially-Robust TD Learning with Markovian Data: Finite-Time Rates and Fundamental Limits