PRISM-XR: Empowering Privacy-Aware XR Collaboration with Multimodal Large Language Models

TL;DR

PRISM-XR tackles privacy risks in cloud-based Multimodal Large Language Model (MLLM) integration for shared XR collaboration by introducing edge-based privacy filtering, explicit user consent for cropped frames, and a lightweight, privacy-preserving synchronization pipeline. The approach hinges on three design pillars: privacy-aware frame processing, semi-marker-based user registration, and content synchronization tailored to MLLM-driven XR, enabling co-located multi-user interactions without exposing raw imagery. Empirical results show near 90% task accuracy with fast registration (<0.27 s) and spatial consistency under 3.5 cm, complemented by an IRB-approved study where highly sensitive content was filtered in over 90% of scenarios and usability remained strong. The framework is implemented end-to-end and open-source, demonstrating practical viability and identifying key avenues for reducing latency, enhancing wake-word robustness, and scaling to larger user groups.

Abstract

Multimodal Large Language Models (MLLMs) enhance collaboration in Extended Reality (XR) environments by enabling flexible object and animation creation through the combination of natural language and visual inputs. However, visual data captured by XR headsets includes real-world backgrounds that may contain irrelevant or sensitive user information, such as credit cards left on the table or facial identities of other users. Uploading those frames to cloud-based MLLMs poses serious privacy risks, particularly when such data is processed without explicit user consent. Additionally, existing colocation and synchronization mechanisms in commercial XR APIs rely on time-consuming, privacy-invasive environment scanning and struggle to adapt to the highly dynamic nature of MLLM-integrated XR environments. In this paper, we propose PRISM-XR, a novel framework that facilitates multi-user collaboration in XR by providing privacy-aware MLLM integration. PRISM-XR employs intelligent frame preprocessing on the edge server to filter sensitive data and remove irrelevant context before communicating with cloud generative AI models. Additionally, we introduce a lightweight registration process and a fully customizable content-sharing mechanism to enable efficient, accurate, and privacy-preserving content synchronization among users. Our numerical evaluation results indicate that the proposed platform achieves nearly 90% accuracy in fulfilling user requests and less than 0.27 seconds registration time while maintaining spatial inconsistencies of less than 3.5 cm. Furthermore, we conducted an IRB-approved user study with 28 participants, demonstrating that our system could automatically filter highly sensitive objects in over 90% of scenarios while maintaining strong overall usability.

Figures (8)

• Figure 1: System architecture of PRISM-XR.
• Figure 2: Workflow of privacy-aware frame processing.
• Figure 3: Examples of critical steps in privacy-aware frame processing.
• Figure 4: Successful user registration with a wire-frame cube.
• Figure 5: Registration evaluation.