Augmented/Mixed Reality (AR/MR) devices are unique from other mobile systems because of their capability to offer an immersive multi-user collaborative experience. While previous studies have explored privacy and security aspects of multiple user interactions in AR/MR, a less-explored area is the vulnerability of gait privacy. Gait is considered a private state because it is a highly individualistic and a distinctive biometric trait. Thus, preserving gait privacy in emerging AR/MR systems is crucial to safeguard individuals from potential identity tracking and unauthorized profiling. This paper first introduces GaitExtract, a framework designed to automatically detect gait information in humans, shedding light on the nuances of gait privacy in AR/MR. In this paper, we designed GaitExtract, a framework that can automatically detect the outside gait information of a human and investigate the vulnerability of gait privacy in AR. In a user study with $20$ participants, our findings reveal that participants were uniquely identifiable with an accuracy of up to $78\%$ using GaitExtract. Consequently, we propose GaitGuard, a system that safeguards gait information of people appearing in the camera view of the AR/MR device. Furthermore, we tested GaitGuard in an MR collaborative application, achieving $22$ fps while streaming mitigated frames to the collaborative server. Our user-study survey indicated that users are more comfortable with releasing videos of them walking when GaitGuard is applied to the frames. These results underscore the efficacy and practicality of GaitGuard in mitigating gait privacy concerns in MR contexts.

翻译：增强现实/混合现实（AR/MR）设备因其提供沉浸式多用户协作体验的能力而区别于其他移动系统。虽然先前研究已探讨了AR/MR中多用户交互的隐私与安全方面，但步态隐私的脆弱性仍是一个较少探索的领域。步态被视为一种私密状态，因为它是一种高度个性化且独特的生物特征。因此，在新兴的AR/MR系统中保护步态隐私，对于防止个人身份追踪和未经授权的特征分析至关重要。本文首先介绍GaitExtract——一个旨在自动检测人类步态信息的框架，揭示了AR/MR中步态隐私的细微差别。我们设计了GaitExtract框架，能够自动检测人体外部的步态信息，并探究AR中步态隐私的脆弱性。在包含20名参与者的用户研究中，我们的发现表明，使用GaitExtract识别参与者的唯一准确率高达78%。为此，我们提出GaitGuard系统，用于保护出现在AR/MR设备摄像头视野中人物的步态信息。此外，我们在一个MR协作应用中测试了GaitGuard，在向协作服务器传输缓解后帧时实现了22帧/秒的速率。我们的用户调研表明，当对帧应用GaitGuard后，用户对发布自己行走视频的舒适度显著提高。这些结果证明了GaitGuard在缓解MR场景中步态隐私问题方面的有效性和实用性。