mlsanityData to 7 Oct 2026

Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning

arXiv 2307.07670 ↗First posted 15 Jul 2023cs.LG cs.AI cs.CRcited by 9

Not on the map. Why?

Abstract (arXiv)

Due to the broad range of applications of multi-agent reinforcement learning (MARL), understanding the effects of adversarial attacks against MARL model is essential for the safe applications of this model. Motivated by this, we investigate the impact of adversarial attacks on MARL. In the considered setup, there is an exogenous attacker who is able to modify the rewards before the agents receive them or manipulate the actions before the environment receives them. The attacker aims to guide each agent into a target policy or maximize the cumulative rewards under some specific reward function chosen by the attacker, while minimizing the amount of manipulation on feedback and action. We first show the limitations of the action poisoning only attacks and the reward poisoning only attacks. We then introduce a mixed attack strategy with both the action poisoning and the reward poisoning. We show that the mixed attack strategy can efficiently attack MARL agents even if the attacker has no prior information about the underlying environment and the agents' algorithms.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 32 of its 41 references that are in the map. First posted on arXiv 15 Jul 2023.

Builds on

32 of 41 references.

References · 32

  1. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  2. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 555
  3. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 308
  4. 2016Safe, Multi-Agent, Reinforcement Learning for Autonomous Drivingcited by 301
  5. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 209
  6. 2019A Review of Cooperative Multi-Agent Deep Reinforcement Learningcited by 147
  7. 2020Provable Self-Play Algorithms for Competitive Reinforcement Learningcited by 112
  8. 2021V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RLcited by 111
  9. 2020A Sharp Analysis of Model-based Reinforcement Learning with Self-Playcited by 104
  10. 2020Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibriumcited by 100
  11. 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
  12. 2020Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexitycited by 91
20 more
  1. 2020Adaptive Reward-Poisoning Attacks against Reinforcement Learningcited by 86
  2. 2020Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learningcited by 81
  3. 2019Corruption-robust exploration in episodic reinforcement learningcited by 72
  4. 2019Policy Poisoning in Batch Reinforcement Learning and Controlcited by 70
  5. 2021BACKDOORL: Backdoor Attack against Competitive Reinforcement Learningcited by 66
  6. 2019Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signalscited by 50
  7. 2021A Model Selection Approach for Corruption Robust Reinforcement Learningcited by 45
  8. 2021Provably Efficient Reinforcement Learning in Decentralized General-Sum Markov Gamescited by 42
  9. 2019Solving Discounted Stochastic Two-Player Games with Near-Optimal Time and Sample Complexitycited by 41
  10. 2020Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamicscited by 38
  11. 2021Robust Policy Gradient against Strong Data Corruptioncited by 30
  12. 2021Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learningcited by 29
  13. 2021Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environmentscited by 26
  14. 2022Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learningcited by 21
  15. 2021Defense Against Reward Poisoning Attacks in Reinforcement Learningcited by 20
  16. 2021Improved Corruption Robust Algorithms for Episodic Reinforcement Learningcited by 20
  17. 2022Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learningcited by 19
  18. 2023Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attackscited by 14
  19. 2022Byzantine-Robust Online and Offline Distributed Reinforcement Learningcited by 13
  20. 2021Game Redesign in No-regret Game Playingcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 5; 2026: 1.

9 papers.

  1. 2025Seven Security Challenges in Cross-domain Multi-agent LLM Systemscited by 12
  2. 2024Online Poisoning Attack Against Reinforcement Learning under Black-box Environmentscited by 2
  3. 2025TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Modelscited by 2
  4. 2023Optimal Cost Constrained Adversarial Attacks For Multiple Agent Systemscited by 1
  5. 2024Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learningcited by 1
  6. 2025Policy Disruption in Reinforcement Learning:Adversarial Attack with Large Language Models and Critical State Identificationcited by 0
  7. 2025Constrained Black-Box Attacks Against Cooperative Multi-Agent Reinforcement Learningcited by 0
  8. 2025Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approachcited by 0
  9. 2026Efficient Preference Poisoning Attack on Offline RLHFcited by 0