mlsanityData to 7 Oct 2026

Adversarial joint attacks on legged robots

arXiv 2205.10098 ↗First posted 20 May 2022cs.RO cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

We address adversarial attacks on the actuators at the joints of legged robots trained by deep reinforcement learning. The vulnerability to the joint attacks can significantly impact the safety and robustness of legged robots. In this study, we demonstrate that the adversarial perturbations to the torque control signals of the actuators can significantly reduce the rewards and cause walking instability in robots. To find the adversarial torque perturbations, we develop black-box adversarial attacks, where, the adversary cannot access the neural networks trained by deep reinforcement learning. The black box attack can be applied to legged robots regardless of the architecture and algorithms of deep reinforcement learning. We employ three search methods for the black-box adversarial attacks: random search, differential evolution, and numerical gradient descent methods. In experiments with the quadruped robot Ant-v2 and the bipedal robot Humanoid-v2, in OpenAI Gym environments, we find that differential evolution can efficiently find the strongest torque perturbations among the three methods. In addition, we realize that the quadruped robot Ant-v2 is vulnerable to the adversarial perturbations, whereas the bipedal robot Humanoid-v2 is robust to the perturbations. Consequently, the joint attacks can be used for proactive diagnosis of robot walking instability.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 16 of its 19 references that are in the map. First posted on arXiv 20 May 2022.

Builds on

16 of 19 references.

References · 16

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  6. 2017Robust Adversarial Reinforcement Learningcited by 439
  7. 2017Adversarial Attacks on Neural Network Policiescited by 314
  8. 2020Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observationscited by 235
  9. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 209
  10. 2019Action Robust Reinforcement Learning and Applications in Continuous Controlcited by 167
  11. 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 152
  12. 2021Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robotscited by 95
4 more
  1. 2020Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learningcited by 61
  2. 2019Characterizing Attacks on Deep Reinforcement Learningcited by 31
  3. 2019Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agentscited by 24
  4. 2020Fault-Aware Robust Control via Adversarial Reinforcement Learningcited by 5

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2024Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllerscited by 9
  2. 2024Robustness Evaluation of Offline Reinforcement Learning for Robot Control Against Action Perturbationscited by 1
  3. 2025Rigid Body Adversarial Attackscited by 0
  4. 2025Adversarial Fine-tuning in Offline-to-Online Reinforcement Learning for Robust Robot Controlcited by 0