基于物理约束的对抗攻击：针对基于卷积的人体运动预测
Physics-constrained Attack against Convolution-based Human Motion Prediction
AI总结：
针对人体运动预测的对抗攻击在自然性和数据规模上存在挑战，本文提出一种基于物理约束的对抗攻击方法，通过最大化预测误差并引入自适应方案与物理约束生成对抗样本，实验证明现有模型易受此攻击影响，并提供了增强鲁棒性的见解。
摘要：
在基于卷积的神经网络的帮助下，人体运动预测已取得卓越性能。然而，目前尚无工作评估人体运动预测在面临对抗攻击时的潜在风险。针对人体运动预测的对抗攻击会在自然性和数据规模方面遇到问题。为解决上述问题，我们提出了一种新的对抗攻击方法，该方法通过在物理约束下最大化人体运动预测器的预测误差来生成最坏情况扰动。具体而言，我们引入了一种新颖的自适应方案，以促进攻击适应目标姿态的尺度，并引入两个物理约束以增强对抗样本的自然性。在三个数据集上的评估实验表明，所有目标模型的预测误差均显著增大，这意味着当前基于卷积的人体运动预测模型易受所提攻击的影响。基于实验结果，我们提供了关于如何增强人体运动预测器对抗鲁棒性以及如何改进针对人体运动预测的对抗攻击的见解。
英文摘要：
Human motion prediction has achieved a brilliant performance with the help of convolution-based neural networks. However, currently, there is no work evaluating the potential risk in human motion prediction when facing adversarial attacks. The adversarial attack will encounter problems against human motion prediction in naturalness and data scale. To solve the problems above, we propose a new adversarial attack method that generates the worst-case perturbation by maximizing the human motion predictor's prediction error with physical constraints. Specifically, we introduce a novel adaptable scheme that facilitates the attack to suit the scale of the target pose and two physical constraints to enhance the naturalness of the adversarial example. The evaluating experiments on three datasets show that the prediction errors of all target models are enlarged significantly, which means current convolution-based human motion prediction models are vulnerable to the proposed attack. Based on the experimental results, we provide insights on how to enhance the adversarial robustness of the human motion predictor and how to improve the adversarial attack against human motion prediction.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
