# Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllers

arXiv: https://arxiv.org/abs/2405.12424 · HTML: https://mlsanity.com/paper/2405.12424/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 53 of its 73 references that are in the map.
- First posted on arXiv 21 May 2024.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 30 of 53)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [Learning agile and dynamic motor skills for legged robots](https://mlsanity.com/paper/1901.08652/) (2019)
- [Robust Adversarial Reinforcement Learning](https://mlsanity.com/paper/1703.02702/) (2017)
- [Learning robust perceptive locomotion for quadrupedal robots in the wild](https://mlsanity.com/paper/2201.08117/) (2022)
- [Adversarial Attacks on Neural Network Policies](https://mlsanity.com/paper/1702.02284/) (2017)
- [Learning Agile Robotic Locomotion Skills by Imitating Animals](https://mlsanity.com/paper/2004.00784/) (2020)
- [Adversarial Policies: Attacking Deep Reinforcement Learning](https://mlsanity.com/paper/1905.10615/) (2019)
- [Rapid Locomotion via Reinforcement Learning](https://mlsanity.com/paper/2205.02824/) (2022)
- [Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims](https://mlsanity.com/paper/2004.07213/) (2020)
- [Extreme Parkour with Legged Robots](https://mlsanity.com/paper/2309.14341/) (2023)
- [Robust Deep Reinforcement Learning with Adversarial Attacks](https://mlsanity.com/paper/1712.03632/) (2017)
- [ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots](https://mlsanity.com/paper/2306.14874/) (2023)
- [Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots](https://mlsanity.com/paper/2103.14295/) (2021)
- [Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition](https://mlsanity.com/paper/2011.01387/) (2020)
- [Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning](https://mlsanity.com/paper/2105.08328/) (2021)
- [Learning Smooth Neural Functions via Lipschitz Regularization](https://mlsanity.com/paper/2202.08345/) (2022)
- [Neural Lander: Stable Drone Landing Control using Learned Dynamics](https://mlsanity.com/paper/1811.08027/) (2018)
- [Adaptive Stress Testing for Autonomous Vehicles](https://mlsanity.com/paper/1902.01909/) (2019)
- [Multi-expert learning of adaptive legged locomotion](https://mlsanity.com/paper/2012.05810/) (2020)
- [Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotion](https://mlsanity.com/paper/2011.02404/) (2020)
- [Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations](https://mlsanity.com/paper/2206.11693/) (2022)

## Built on by (most cited first, 14 of 14)

- [FACET: Force-Adaptive Control via Impedance Reference Tracking for Legged Robots](https://mlsanity.com/paper/2505.06883/) (2025)
- [Feedback Favors the Generalization of Neural ODEs](https://mlsanity.com/paper/2410.10253/) (2024)
- [LiRA: Light-Robust Adversary for Model-based Reinforcement Learning in Real World](https://mlsanity.com/paper/2409.19617/) (2024)
- [GRAM: Generalization in Deep RL with a Robust Adaptation Module](https://mlsanity.com/paper/2412.04323/) (2024)
- [Disturbance-Aware Adaptive Compensation in Hybrid Force-Position Locomotion Policy for Legged Robots](https://mlsanity.com/paper/2506.00472/) (2025)
- [R2DN: Scalable Parameterization of Contracting and Lipschitz Recurrent Deep Networks](https://mlsanity.com/paper/2504.01250/) (2025)
- [Neural Fidelity Calibration for Informative Sim-to-Real Adaptation](https://mlsanity.com/paper/2504.08604/) (2025)
- [Post-Convergence Sim-to-Real Policy Transfer: A Principled Alternative to Cherry-Picking](https://mlsanity.com/paper/2504.15414/) (2025)
- [React to Surprises: Stable-by-Design Neural Feedback Control and the Youla-REN](https://mlsanity.com/paper/2506.01226/) (2025)
- [Bridge the Gap: Enhancing Quadruped Locomotion with Vertical Ground Perturbations](https://mlsanity.com/paper/2510.13488/) (2025)
- [Physics-Informed Eikonal Caging for Whole-Arm Manipulation Planning](https://mlsanity.com/paper/2606.22143/) (2026)
- [Robust RL Control for Bipedal Locomotion with Closed Kinematic Chains](https://mlsanity.com/paper/2507.10164/) (2025)
- [Beyond Model Jailbreak: Systematic Dissection of the "Ten DeadlySins" in Embodied Intelligence](https://mlsanity.com/paper/2512.06387/) (2025)
- [Robustness of Robotic Manipulation: Foundations and Frontiers](https://mlsanity.com/paper/2606.31494/) (2026)

## Abstract (arXiv)

Legged locomotion has recently achieved remarkable success with the progress of machine learning techniques, especially deep reinforcement learning (RL). Controllers employing neural networks have demonstrated empirical and qualitative robustness against real-world uncertainties, including sensor noise and external perturbations. However, formally investigating the vulnerabilities of these locomotion controllers remains a challenge. This difficulty arises from the requirement to pinpoint vulnerabilities across a long-tailed distribution within a high-dimensional, temporally sequential space. As a first step towards quantitative verification, we propose a computational method that leverages sequential adversarial attacks to identify weaknesses in learned locomotion controllers. Our research demonstrates that, even state-of-the-art robust controllers can fail significantly under well-designed, low-magnitude adversarial sequence. Through experiments in simulation and on the real robot, we validate our approach's effectiveness, and we illustrate how the results it generates can be used to robustify the original policy and offer valuable insights into the safety of these black-box policies. Project page: https://fanshi14.github.io/me/rss24.html