The emergence of mobile social metaverses, a novel paradigm bridging physical and virtual realms, has led to the widespread adoption of avatars as digital representations for Social Metaverse Users (SMUs) within virtual spaces. Equipped with immersive devices, SMUs leverage Edge Servers (ESs) to deploy their avatars and engage with other SMUs in virtual spaces. To enhance immersion, SMUs incline to opt for 3D avatars for social interactions. However, existing 3D avatars are typically generated through scanning the real faces of SMUs, which can raise concerns regarding information privacy and security, such as profile identity leakages. To tackle this, we introduce a new framework for personalized 3D avatar construction, leveraging a two-layer network model that provides SMUs with the option to customize their personal avatars for privacy preservation. Specifically, our approach introduces avatar pseudonyms to jointly safeguard the profile and digital identity privacy of the generated avatars. Then, we design a novel metric named Privacy of Personalized Avatars (PoPA), to evaluate effectiveness of the avatar pseudonyms. To optimize pseudonym resource, we model the pseudonym distribution process as a Stackelberg game and employ Deep Reinforcement Learning (DRL) to learn equilibrium strategies under incomplete information. Simulation results validate the efficacy and feasibility of our proposed schemes for mobile social metaverses.

翻译：移动社交元宇宙作为一种连接物理与虚拟世界的新兴范式，其出现使得化身作为社交元宇宙用户在虚拟空间中的数字表征得到广泛应用。社交元宇宙用户借助沉浸式设备，通过边缘服务器部署其化身并在虚拟空间中与其他用户互动。为提升沉浸感，用户倾向于选择三维化身进行社交交互。然而，现有三维化身通常通过扫描用户真实面部生成，这可能引发信息隐私与安全问题，例如个人身份信息泄露。为解决此问题，我们提出一种基于双层网络模型的个性化三维化身构建框架，使用户能够通过定制个人化化身以实现隐私保护。具体而言，本方法引入化身化名机制，协同保护生成化身的个人档案与数字身份隐私。随后，我们设计了一种名为"个性化化身隐私度"的新度量指标，用以评估化身化名的保护效能。为优化化名资源配置，我们将化名分配过程建模为斯坦克尔伯格博弈，并采用深度强化学习在不完全信息条件下学习均衡策略。仿真结果验证了所提方案在移动社交元宇宙中的有效性与可行性。