Local Features Meet Stochastic Anonymization: Revolutionizing Privacy-Preserving Face Recognition for Black-Box Models

TL;DR

This document provides the CVPR 2025 submission guidelines and formatting rules for manuscripts. It covers page limits, layout (two-column), font choices, numbering, blind review anonymization, and how to handle references, figures, and color to ensure consistent, readable proceedings. It also prescribes required elements for the review version (ruler, page numbers) and the final copy (copyright release), aiming to standardize submissions and uphold fair, trackable review processes.

Abstract

The task of privacy-preserving face recognition (PPFR) currently faces two major unsolved challenges: (1) existing methods are typically effective only on specific face recognition models and struggle to generalize to black-box face recognition models; (2) current methods employ data-driven reversible representation encoding for privacy protection, making them susceptible to adversarial learning and reconstruction of the original image. We observe that face recognition models primarily rely on local features ({e.g., face contour, skin texture, and so on) for identification. Thus, by disrupting global features while enhancing local features, we achieve effective recognition even in black-box environments. Additionally, to prevent adversarial models from learning and reversing the anonymization process, we adopt an adversarial learning-based approach with irreversible stochastic injection to ensure the stochastic nature of the anonymization. Experimental results demonstrate that our method achieves an average recognition accuracy of 94.21\% on black-box models, outperforming existing methods in both privacy protection and anti-reconstruction capabilities.

Figures (2)

• Figure 1: Example of caption. It is set in Roman so that mathematics (always set in Roman: $B \sin A = A \sin B$) may be included without an ugly clash.
• Figure 2: Example of a short caption, which should be centered.