Hide and Seek: How Does Watermarking Impact Face Recognition?

TL;DR

This paper examines how digital watermarking affects face recognition performance, revealing a trade-off between robust image attribution and recognition accuracy, especially in challenging face images, and discusses implications for responsible use of generative models.

Contribution

It introduces a novel watermarking scheme integrated with face recognition, systematically analyzing its impact and highlighting the trade-offs involved.

Findings

Watermarking enables robust image attribution.

It causes a slight decline in face recognition accuracy.

Training on watermarked images offers limited performance improvement.

Abstract

The recent progress in generative models has revolutionized the synthesis of highly realistic images, including face images. This technological development has undoubtedly helped face recognition, such as training data augmentation for higher recognition accuracy and data privacy. However, it has also introduced novel challenges concerning the responsible use and proper attribution of computer generated images. We investigate the impact of digital watermarking, a technique for embedding ownership signatures into images, on the effectiveness of face recognition models. We propose a comprehensive pipeline that integrates face image generation, watermarking, and face recognition to systematically examine this question. The proposed watermarking scheme, based on an encoder-decoder architecture, successfully embeds and recovers signatures from both real and synthetic face images while preserving their visual fidelity. Through extensive experiments, we unveil that while watermarking enables robust image attribution, it results in a slight decline in face recognition accuracy, particularly evident for face images with challenging poses and expressions. Additionally, we find that directly training face recognition models on watermarked images offers only a limited alleviation of this performance decline. Our findings underscore the intricate trade off between watermarking and face recognition accuracy. This work represents a pivotal step towards the responsible utilization of generative models in face recognition and serves to initiate discussions regarding the broader implications of watermarking in biometrics.