# Deep-Attack over the Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2205.00807 · HTML: https://mlsanity.com/paper/2205.00807/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 32 references that are in the map.
- First posted on arXiv 2 May 2022.

## Builds on (most cited first, 27 of 27)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Robust Adversarial Reinforcement Learning](https://mlsanity.com/paper/1703.02702/) (2017)
- [Adversarial Attacks on Neural Network Policies](https://mlsanity.com/paper/1702.02284/) (2017)
- [Tactics of Adversarial Attack on Deep Reinforcement Learning Agents](https://mlsanity.com/paper/1703.06748/) (2017)
- [Robust Deep Reinforcement Learning with Adversarial Attacks](https://mlsanity.com/paper/1712.03632/) (2017)
- [Delving into adversarial attacks on deep policies](https://mlsanity.com/paper/1705.06452/) (2017)
- [Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks](https://mlsanity.com/paper/1701.04143/) (2017)
- [Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning](https://mlsanity.com/paper/2005.07099/) (2020)
- [MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples](https://mlsanity.com/paper/1711.08478/) (2017)
- [Whatever Does Not Kill Deep Reinforcement Learning, Makes It Stronger](https://mlsanity.com/paper/1712.09344/) (2017)
- [Deep Reinforcement Learning based Automatic Exploration for Navigation in Unknown Environment](https://mlsanity.com/paper/2007.11808/) (2020)
- [Characterizing Attacks on Deep Reinforcement Learning](https://mlsanity.com/paper/1907.09470/) (2019)
- [TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents](https://mlsanity.com/paper/1903.06638/) (2019)
- [Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agents](https://mlsanity.com/paper/1909.02583/) (2019)
- [Optimal Attacks on Reinforcement Learning Policies](https://mlsanity.com/paper/1907.13548/) (2019)
- [Reinforcement Learning for Autonomous Defence in Software-Defined Networking](https://mlsanity.com/paper/1808.05770/) (2018)
- [Sequential Attacks on Agents for Long-Term Adversarial Goals](https://mlsanity.com/paper/1805.12487/) (2018)
- [Blackbox Attacks on Reinforcement Learning Agents Using Approximated Temporal Information](https://mlsanity.com/paper/1909.02918/) (2019)
- [Variance Networks: When Expectation Does Not Meet Your Expectations](https://mlsanity.com/paper/1803.03764/) (2018)
- [Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noise](https://mlsanity.com/paper/1806.02190/) (2018)
- [Adversary A3C for Robust Reinforcement Learning](https://mlsanity.com/paper/1912.00330/) (2019)
- [Phonetic-enriched Text Representation for Chinese Sentiment Analysis with Reinforcement Learning](https://mlsanity.com/paper/1901.07880/) (2019)
- [Graph Routing between Capsules](https://mlsanity.com/paper/2106.11531/) (2021)
- [Analysis and Improvement of Adversarial Training in DQN Agents With Adversarially-Guided Exploration (AGE)](https://mlsanity.com/paper/1906.01119/) (2019)

## Built on by (most cited first, 5 of 5)

- [Flexible Physical Camouflage Generation Based on a Differential Approach](https://mlsanity.com/paper/2402.13575/) (2024)
- [DOEPatch: Dynamically Optimized Ensemble Model for Adversarial Patches Generation](https://mlsanity.com/paper/2312.16907/) (2023)
- [LP-BFGS attack: An adversarial attack based on the Hessian with limited pixels](https://mlsanity.com/paper/2210.15446/) (2022)
- [CuDA2: An approach for Incorporating Traitor Agents into Cooperative Multi-Agent Systems](https://mlsanity.com/paper/2406.17425/) (2024)
- [PGN: A perturbation generation network against deep reinforcement learning](https://mlsanity.com/paper/2312.12904/) (2023)

## 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.