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：基于骨架的动作识别因其数据集轻量、紧凑的特性而受到实践者和研究者的关注。与基于RGB视频的动作识别相比，基于骨架的动作识别在保持竞争性识别性能的同时，能更安全地保护受试者隐私。然而，随着骨架识别算法以及运动和深度传感器的改进，骨架数据集中能保留更多运动特征的细节，从而导致潜在的隐私泄露。我们首先训练分类器从骨架轨迹中分类隐私信息，以研究骨架数据集潜在的隐私泄露问题。初步实验表明，使用Shift-GCN、MS-G3D和2s-AGCN三种基线模型时，性别分类器平均准确率达到87%，重识别分类器平均准确率达到80%。我们提出了一种基于对抗学习的匿名化框架，以保护骨架数据集潜在的隐私泄露风险。实验结果表明，即使采用简单的匿名化架构，匿名化后的数据集也能在降低隐私泄露风险的同时，对动作识别性能产生微小影响。我们实验中使用的代码可在https://github.com/ml-postech/Skeleton-anonymization/获取。