mlsanityData to 7 Oct 2026

Deep-Attack over the Deep Reinforcement Learning

arXiv 2205.00807 ↗First posted 2 May 2022cs.LG cs.AI cs.CRcited by 5

Not on the map. Why?

Abstract (arXiv)

Recent adversarial attack developments have made reinforcement learning more vulnerable, and different approaches exist to deploy attacks against it, where the key is how to choose the right timing of the attack. Some work tries to design an attack evaluation function to select critical points that will be attacked if the value is greater than a certain threshold. This approach makes it difficult to find the right place to deploy an attack without considering the long-term impact. In addition, there is a lack of appropriate indicators of assessment during attacks. To make the attacks more intelligent as well as to remedy the existing problems, we propose the reinforcement learning-based attacking framework by considering the effectiveness and stealthy spontaneously, while we also propose a new metric to evaluate the performance of the attack model in these two aspects. Experimental results show the effectiveness of our proposed model and the goodness of our proposed evaluation metric. Furthermore, we validate the transferability of the model, and also its robustness under the adversarial training.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 27 of its 32 references that are in the map. First posted on arXiv 2 May 2022.

Builds on

27 of 32 references.

References · 27

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2017Robust Adversarial Reinforcement Learningcited by 439
  6. 2017Adversarial Attacks on Neural Network Policiescited by 314
  7. 2017Tactics of Adversarial Attack on Deep Reinforcement Learning Agentscited by 163
  8. 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 152
  9. 2017Delving into adversarial attacks on deep policiescited by 104
  10. 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
  11. 2020Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learningcited by 62
  12. 2017MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examplescited by 46
15 more
  1. 2017Whatever Does Not Kill Deep Reinforcement Learning, Makes It Strongercited by 35
  2. 2019Characterizing Attacks on Deep Reinforcement Learningcited by 31
  3. 2019TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agentscited by 29
  4. 2020Deep Reinforcement Learning based Automatic Exploration for Navigation in Unknown Environmentcited by 29
  5. 2019Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agentscited by 24
  6. 2019Optimal Attacks on Reinforcement Learning Policiescited by 21
  7. 2018Reinforcement Learning for Autonomous Defence in Software-Defined Networkingcited by 17
  8. 2018Sequential Attacks on Agents for Long-Term Adversarial Goalscited by 16
  9. 2019Blackbox Attacks on Reinforcement Learning Agents Using Approximated Temporal Informationcited by 13
  10. 2018Variance Networks: When Expectation Does Not Meet Your Expectationscited by 9
  11. 2018Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noisecited by 7
  12. 2019Adversary A3C for Robust Reinforcement Learningcited by 6
  13. 2019Phonetic-enriched Text Representation for Chinese Sentiment Analysis with Reinforcement Learningcited by 5
  14. 2021Graph Routing between Capsulescited by 5
  15. 2019Analysis and Improvement of Adversarial Training in DQN Agents With Adversarially-Guided Exploration (AGE)cited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 2.

5 papers.

  1. 2024Flexible Physical Camouflage Generation Based on a Differential Approachcited by 7
  2. 2023DOEPatch: Dynamically Optimized Ensemble Model for Adversarial Patches Generationcited by 5
  3. 2022LP-BFGS attack: An adversarial attack based on the Hessian with limited pixelscited by 3
  4. 2024CuDA2: An approach for Incorporating Traitor Agents into Cooperative Multi-Agent Systemscited by 1
  5. 2023PGN: A perturbation generation network against deep reinforcement learningcited by 0