标题： AdvGrasp：从物理角度对机器人抓取的对抗攻击 显示英文标题

标题： AdvGrasp: Adversarial Attacks on Robotic Grasping from a Physical Perspective

摘要： 对抗性攻击在机器人抓取中的应用为评估和提高这些系统的鲁棒性提供了有价值的见解。 与仅关注神经网络预测而忽视抓取物理原理的研究不同，本文从物理角度引入了AdvGrasp，这是一种针对机器人抓取的对抗性攻击框架。 具体而言，AdvGrasp针对两个核心方面：提升能力，即评估克服重力提升物体的能力，以及抓取稳定性，即评估对外部干扰的抵抗能力。 通过变形物体形状以增加力矩空间中的重力扭矩并减少稳定性裕度，我们的方法系统地降低了这两个关键抓取指标，生成破坏抓取性能的对抗性物体。 在多种场景下的大量实验验证了AdvGrasp的有效性，而现实世界的验证展示了其鲁棒性和实际适用性。 显示英文摘要

摘要： 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