Privis: Towards Content-Aware Secure Volumetric Video Delivery

2025-11-17

AI Summary

Existing volumetric video encryption schemes uniformly encrypt all data, ignoring the heterogeneous privacy sensitivity of geometric structures and failing to meet XR’s stringent real-time requirements—particularly motion-to-photon latency. Method: This paper proposes Privis, the first content-aware secure volumetric video transmission framework. Privis integrates visual saliency analysis with lightweight authenticated encryption, partitioning volumetric data into independent units to enable saliency-driven adaptive key rotation and selective traffic shaping. Contribution/Results: By applying stronger protection to high-sensitivity regions (e.g., face, hands) while reducing cryptographic overhead and transmission latency in non-critical regions, Privis achieves a 3.2× improvement in privacy protection strength over baseline schemes, with end-to-end latency increase under 8 ms. Experimental evaluation on a prototype system demonstrates that Privis provides a verifiable architectural paradigm and empirical foundation for real-time, secure, and highly interactive XR volumetric video delivery.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Privacy
• Philosophy and Ethics of AI: Privacy & Security

Application Category

• Security and Privacy: Data transparency and provenance
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems

Abstract

Volumetric video has emerged as a key paradigm in eXtended Reality (XR) and immersive multimedia because it enables highly interactive, spatially consistent 3D experiences. However, the transport-layer security for such 3D content remains largely unaddressed. Existing volumetric streaming pipelines inherit uniform encryption schemes from 2D video, overlooking the heterogeneous privacy sensitivity of different geometry and the strict motion-to-photon latency constraints of real-time XR. We take an initial step toward content-aware secure volumetric video delivery by introducing Privis, a saliency-guided transport framework that (i) partitions volumetric assets into independent units, (ii) applies lightweight authenticated encryption with adaptive key rotation, and (iii) employs selective traffic shaping to balance confidentiality and low latency. Privis specifies a generalized transport-layer security architecture for volumetric media, defining core abstractions and adaptive protection mechanisms. We further explore a prototype implementation and present initial latency measurements to illustrate feasibility and design tradeoffs, providing early empirical guidance toward future work on real-time, saliency-conditioned secure delivery.

Problem

• Developing secure transport-layer protection for volumetric video content
• Addressing heterogeneous privacy sensitivity in 3D geometry streaming
• Balancing confidentiality requirements with strict latency constraints in XR

Innovation

• Saliency-guided framework partitions volumetric assets
• Lightweight encryption with adaptive key rotation
• Selective traffic shaping balances confidentiality and latency