Proceedings

AdvGrasp: Adversarial Attacks on Robotic Grasping from a Physical Perspective

Xiaofei Wang, Mingliang Han, Tianyu Hao, Cegang Li, Yunbo Zhao, Keke Tang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 547-555.

https://doi.org/10.24963/ijcai.2025/62

Keywords

  • Robotics: ROB: Manipulation
  • Machine Learning: ML: Trustworthy machine learning
  • AI Ethics, Trust, Fairness: ETF: Safety and robustness
  • Machine Learning: ML: Adversarial machine learning

Abstract

Adversarial attacks on robotic grasping provide valuable insights into evaluating and improving the robustness of these systems. Unlike studies that focus solely on neural network predictions while overlooking the physical principles of grasping, this paper introduces AdvGrasp, a framework for adversarial attacks on robotic grasping from a physical perspective. Specifically, AdvGrasp targets two core aspects: lift capability, which evaluates the ability to lift objects against gravity, and grasp stability, which assesses resistance to external disturbances. By deforming the object's shape to increase gravitational torque and reduce stability margin in the wrench space, our method systematically degrades these two key grasping metrics, generating adversarial objects that compromise grasp performance. Extensive experiments across diverse scenarios validate the effectiveness of AdvGrasp, while real-world validations demonstrate its robustness and practical applicability.

Xiaofei Wang, Mingliang Han, Tianyu Hao, Cegang Li, Yunbo Zhao, and Keke Tang. 2025. AdvGrasp: Adversarial Attacks on Robotic Grasping from a Physical Perspective. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 547–555. https://doi.org/10.24963/ijcai.2025/62
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards