# Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks

arXiv: https://arxiv.org/abs/2503.20844 · HTML: https://mlsanity.com/paper/2503.20844/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods.
- Builds on 51 of its 77 references that are in the map.
- First posted on arXiv 26 Mar 2025.

## Placed in

- Deep reinforcement learning methods / [Adversarial robustness and RL in finance](https://mlsanity.com/deeprl/adversarial-robustness-and-rl-in-finance/)

## Builds on (most cited first, 30 of 51)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [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)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)
- [Ensemble Adversarial Training: Attacks and Defenses](https://mlsanity.com/paper/1705.07204/) (2017)
- [Fast is better than free: Revisiting adversarial training](https://mlsanity.com/paper/2001.03994/) (2020)
- [Improving Transferability of Adversarial Examples with Input Diversity](https://mlsanity.com/paper/1803.06978/) (2018)
- [Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks](https://mlsanity.com/paper/1904.02884/) (2019)
- [Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks](https://mlsanity.com/paper/1908.06281/) (2019)
- [Adversarial Attacks on Neural Network Policies](https://mlsanity.com/paper/1702.02284/) (2017)
- [Adversarial Attacks and Defences: A Survey](https://mlsanity.com/paper/1810.00069/) (2018)
- [Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations](https://mlsanity.com/paper/2003.08938/) (2020)
- [Tactics of Adversarial Attack on Deep Reinforcement Learning Agents](https://mlsanity.com/paper/1703.06748/) (2017)
- [Admix: Enhancing the Transferability of Adversarial Attacks](https://mlsanity.com/paper/2102.00436/) (2021)
- [Robust Deep Reinforcement Learning with Adversarial Attacks](https://mlsanity.com/paper/1712.03632/) (2017)
- [Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark](https://mlsanity.com/paper/2310.12567/) (2023)
- [Advances in adversarial attacks and defenses in computer vision: A survey](https://mlsanity.com/paper/2108.00401/) (2021)
- [SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation](https://mlsanity.com/paper/2011.07215/) (2020)
- [Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks](https://mlsanity.com/paper/2303.15991/) (2023)
- [Diffusion Models for Imperceptible and Transferable Adversarial Attack](https://mlsanity.com/paper/2305.08192/) (2023)
- [Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity](https://mlsanity.com/paper/2208.05767/) (2022)
- [Robust Deep Reinforcement Learning through Adversarial Loss](https://mlsanity.com/paper/2008.01976/) (2020)
- [Content-based Unrestricted Adversarial Attack](https://mlsanity.com/paper/2305.10665/) (2023)
- [Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network](https://mlsanity.com/paper/1810.01279/) (2018)
- [AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networks](https://mlsanity.com/paper/2403.13101/) (2024)
- [SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Models](https://mlsanity.com/paper/2407.00952/) (2024)

## Built on by (most cited first, 7 of 7)

- [LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systems](https://mlsanity.com/paper/2511.19368/) (2025)
- [LEED: A Highly Efficient and Scalable LLM-Empowered Expert Demonstrations Framework for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2509.14680/) (2025)
- [Defensive Adversarial CAPTCHA: A Semantics-Driven Framework for Natural Adversarial Example Generation](https://mlsanity.com/paper/2506.10685/) (2025)
- [Sample Efficient Experience Replay in Non-stationary Environments](https://mlsanity.com/paper/2509.15032/) (2025)
- [SFL-LEO: Asynchronous Split-Federated Learning Design for LEO Satellite-Ground Network Framework](https://mlsanity.com/paper/2504.13479/) (2025)
- [SIDeR: Semantic Identity Decoupling for Unrestricted Face Privacy](https://mlsanity.com/paper/2602.04994/) (2026)
- [Large Language Model Enhanced Differentiable Trajectory Planning for IoT-Enabled Autonomous Driving](https://mlsanity.com/paper/2607.10438/) (2026)

## Abstract (arXiv)

Deep reinforcement learning (DRL) has emerged as a promising approach for robotic control, but its realworld deployment remains challenging due to its vulnerability to environmental perturbations. Existing white-box adversarial attack methods, adapted from supervised learning, fail to effectively target DRL agents as they overlook temporal dynamics and indiscriminately perturb all state dimensions, limiting their impact on long-term rewards. To address these challenges, we propose the Adaptive Gradient-Masked Reinforcement (AGMR) Attack, a white-box attack method that combines DRL with a gradient-based soft masking mechanism to dynamically identify critical state dimensions and optimize adversarial policies. AGMR selectively allocates perturbations to the most impactful state features and incorporates a dynamic adjustment mechanism to balance exploration and exploitation during training. Extensive experiments demonstrate that AGMR outperforms state-of-the-art adversarial attack methods in degrading the performance of the victim agent and enhances the victim agent's robustness through adversarial defense mechanisms.