Capturing skeleton data is an important area of computer vision, especially for use in a virtual reality (VR) setting. As new techniques to extract skeletons come out, the popularity of skeleton-based motion data has increased. While the skeleton data appears to be anonymous, it can be exploited to discover personally identifiable information (PII). This poses a risk of unintentional privacy leakages when skeletons are publicly displayed, like in a VR environment. We explore the privacy implications posed by the skeleton data, focusing on the privacy and utility trade-off and current privacy-preserving techniques. In this paper, we propose a new baseline attack model Linkage Attack Neural Network (LAN) that acts as a matching classifier to distinguish whether two skeleton-sequences are from the same actor. Then we propose a new defense model, the Privacy-centric Deep Motion Retargeting (PMR) model that is an adversarial/cooperatively trained motion retargeting model. Additionally, we incorporate explanation techniques to identify and mask the most privacy-sensitive joints, either by zeroing them out or adding controlled noise. Finally, we propose a transformer-based motion retargeting model designed for real-time applications, leveraging autoregressive decoding for continuous, frame-by-frame skeleton generation.

Skeleton-based motion capture and visualization is an important computer vision task, especially in the virtual reality (VR) environment. It has grown increasingly popular due to the ease of gathering skeleton data and the high demand of virtual socialization. The captured skeleton data seems anonymous but can still be used to extract personal identifiable information (PII). This can lead to an unintended privacy leakage inside a VR meta-verse. We propose a novel linkage attack on skeleton-based motion visualization. It detects if a target and a reference skeleton are the same individual. The proposed model, called Linkage Attack Neural Network (LAN), is based on the principles of a Siamese Network. It incorporates deep neural networks to embed the relevant PII then uses a classifier to match the reference and target skeletons. We also employ classical and deep motion retargeting (MR) to cast the target skeleton onto a dummy skeleton such that the motion sequence is anonymized for privacy protection. Our evaluation shows that the effectiveness of LAN in the linkage attack and the effectiveness of MR in anonymization.