A Survey on Facial Image Privacy Preservation in Cloud-Based Services

2025-01-15

AI Summary

Cloud-based facial recognition services pose severe privacy risks. This paper systematically surveys privacy-preserving techniques for facial images in cloud environments, focusing on two principal approaches: image blurring (e.g., differential privacy-enhanced GAN-based anonymization) and adversarial perturbations (including white-box and black-box robust perturbation generation). We introduce the first structured taxonomy and conduct a cross-dimensional comparative analysis. Furthermore, we propose a scalable privacy-utility co-evaluation framework, quantitatively assessing over 70 state-of-the-art methods using metrics such as recognition accuracy drop rate and SSIM. Our evaluation reveals that blurring methods better suit stringent regulatory compliance scenarios, whereas adversarial perturbations offer greater deployment flexibility. Key technical bottlenecks identified include poor cross-model generalizability and suboptimal real-time performance. The findings provide theoretical foundations and practical guidance for technology selection, standardization efforts, and future research.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Privacy
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

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

Facial recognition models are increasingly employed by commercial enterprises, government agencies, and cloud service providers for identity verification, consumer services, and surveillance. These models are often trained using vast amounts of facial data processed and stored in cloud-based platforms, raising significant privacy concerns. Users' facial images may be exploited without their consent, leading to potential data breaches and misuse. This survey presents a comprehensive review of current methods aimed at preserving facial image privacy in cloud-based services. We categorize these methods into two primary approaches: image obfuscation-based protection and adversarial perturbation-based protection. We provide an in-depth analysis of both categories, offering qualitative and quantitative comparisons of their effectiveness. Additionally, we highlight unresolved challenges and propose future research directions to improve privacy preservation in cloud computing environments.

Problem

• Facial Recognition
• Privacy Leakage
• Cloud Services

Innovation

• Cloud Privacy Protection
• Facial Image Obfuscation
• Error Induction Techniques