Makeup-Guided Facial Privacy Protection via Untrained Neural Network Priors

TL;DR

This paper introduces a novel makeup-guided facial privacy protection method that uses untrained neural networks and test-time optimization to generate natural-looking adversarial makeup, effectively deceiving face recognition systems without dataset bias.

Contribution

The proposed approach uniquely employs an untrained neural network with test-time optimization for privacy protection, eliminating the need for large-scale makeup datasets and reducing bias issues.

Findings

Outperforms existing methods in face verification and identification tasks.

Effectively deceives commercial face recognition systems.

Extends to videos by leveraging temporal correlations.

Abstract

Deep learning-based face recognition (FR) systems pose significant privacy risks by tracking users without their consent. While adversarial attacks can protect privacy, they often produce visible artifacts compromising user experience. To mitigate this issue, recent facial privacy protection approaches advocate embedding adversarial noise into the natural looking makeup styles. However, these methods require training on large-scale makeup datasets that are not always readily available. In addition, these approaches also suffer from dataset bias. For instance, training on makeup data that predominantly contains female faces could compromise protection efficacy for male faces. To handle these issues, we propose a test-time optimization approach that solely optimizes an untrained neural network to transfer makeup style from a reference to a source image in an adversarial manner. We introduce two key modules: a correspondence module that aligns regions between reference and source images in latent space, and a decoder with conditional makeup layers. The untrained decoder, optimized via carefully designed structural and makeup consistency losses, generates a protected image that resembles the source but incorporates adversarial makeup to deceive FR models. As our approach does not rely on training with makeup face datasets, it avoids potential male/female dataset biases while providing effective protection. We further extend the proposed approach to videos by leveraging on temporal correlations. Experiments on benchmark datasets demonstrate superior performance in face verification and identification tasks and effectiveness against commercial FR systems. Our code and models will be available at https://github.com/fahadshamshad/deep-facial-privacy-prior