Skeleton-based action recognition attracts practitioners and researchers due to the lightweight, compact nature of datasets. Compared with RGB-video-based action recognition, skeleton-based action recognition is a safer way to protect the privacy of subjects while having competitive recognition performance. However, due to improvements in skeleton recognition algorithms as well as motion and depth sensors, more details of motion characteristics can be preserved in the skeleton dataset, leading to potential privacy leakage. We first train classifiers to categorize private information from skeleton trajectories to investigate the potential privacy leakage from skeleton datasets. Our preliminary experiments show that the gender classifier achieves 87% accuracy on average, and the re-identification classifier achieves 80% accuracy on average with three baseline models: Shift-GCN, MS-G3D, and 2s-AGCN. We propose an anonymization framework based on adversarial learning to protect potential privacy leakage from the skeleton dataset. Experimental results show that an anonymized dataset can reduce the risk of privacy leakage while having marginal effects on action recognition performance even with simple anonymizer architectures. The code used in our experiments is available at https://github.com/ml-postech/Skeleton-anonymization/
翻译:由于数据集的重量轻、紧凑性质,基于Skeleton的动作识别吸引了从业人员和研究人员。与基于 RGB 的视频动作识别相比,基于骨骼的动作识别是一种在具有竞争性承认性的同时保护主体隐私的更安全的方法。然而,由于骨架识别算法以及运动和深度传感器的改进,可以在骨架数据集中保存更多关于运动特征的细节,从而可能导致隐私渗漏。我们首先训练分类人员对来自骨架轨迹的私人信息进行分类,以调查骨架数据集潜在的隐私渗漏。我们的初步实验显示,性别分类员平均达到87%的准确度,而重新确定身份分类员在三个基线模型中平均达到80%的准确度: Shift-GCN、MS-G3D和2s-AGCN。我们提议了一个基于对抗性学习的匿名化框架,以保护可能从骨架数据集渗漏的隐私。实验结果表明,匿名数据集可以降低隐私渗漏的风险,同时对行动识别性表现产生边际效应,即使使用简单的语系/Scommaximech架构。我们实验中使用的代码在httpsl/Scommakel/skelmelmeximet。