Moderating Embodied Cyber Threats Using Generative AI

The advancement in computing and hardware, like spatial computing and VR headsets (e.g., Apple's Vision Pro) [1], has boosted the popularity of social VR platforms (VRChat, Rec Room, Meta HorizonWorlds) [2, 3, 4]. Unlike traditional digital interactions, social VR allows for more immersive experiences, with avatars that mimic users' real-time movements and enable physical-like interactions. However, the immersive nature of social VR may introduce intensified and more physicalized cyber threats-we define as "embodied cyber threats", including trash-talking, virtual "groping", and such virtual harassment and assault. These new cyber threats are more realistic and invasive due to direct, virtual interactions, underscoring the urgent need for comprehensive understanding and practical strategies to enhance safety and security in virtual environments.