Optimizing QoE-Privacy Tradeoff for Proactive VR Streaming

2025-03-12

AI Summary

In proactive VR streaming, uploading user viewpoints raises serious privacy concerns, as existing noise-addition methods—while offering limited privacy guarantees—sacrifice Quality of Experience (QoE) and cannot achieve zero viewpoint leakage. Method: This paper proposes a novel noise-injection paradigm in the prediction error domain: controlled noise is added to viewpoint prediction residuals rather than raw viewpoints. Contribution/Results: We provide the first theoretical proof and practical realization of strictly zero viewpoint leakage probability. By deriving the optimal residual error distribution, we formulate a joint QoE–privacy optimization model. Through rigorous privacy information-theoretic analysis and simulations, we demonstrate that our approach achieves significantly lower QoE degradation than conventional raw-viewpoint noise injection, while satisfying strict privacy constraints.

Technology Category

• Machine Learning: Privacy
• Computer Vision: Bias, Fairness & Privacy
• Search and Optimization: Learning to Search

Application Category

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

Abstract

Proactive virtual reality (VR) streaming requires users to upload viewpoint-related information, raising significant privacy concerns. Existing strategies preserve privacy by introducing errors to viewpoints, which, however, compromises the quality of experience (QoE) of users. In this paper, we first delve into the analysis of the viewpoint leakage probability achieved by existing privacy-preserving approaches. We determine the optimal distribution of viewpoint errors that minimizes the viewpoint leakage probability. Our analyses show that existing approaches cannot fully eliminate viewpoint leakage. Then, we propose a novel privacy-preserving approach that introduces noise to uploaded viewpoint prediction errors, which can ensure zero viewpoint leakage probability. Given the proposed approach, the tradeoff between privacy preservation and QoE is optimized to minimize the QoE loss while satisfying the privacy requirement. Simulation results validate our analysis results and demonstrate that the proposed approach offers a promising solution for balancing privacy and QoE.

Problem

• Optimizes QoE-privacy tradeoff in VR streaming
• Reduces viewpoint leakage probability effectively
• Introduces noise to ensure zero viewpoint leakage

Innovation

• Introduces noise to viewpoint prediction errors
• Ensures zero viewpoint leakage probability
• Optimizes QoE-privacy tradeoff effectively