Towards Generalized Proactive Defense against Face Swapping with Contour-Hybrid Watermark

TL;DR

This paper proposes a proactive watermarking method called contour-hybrid watermark (CMark) that embeds robust, elaborate watermarks around facial contours to detect face swapping across unknown techniques without prior training on specific methods.

Contribution

It introduces a generalized proactive face swapping detection approach that embeds hybrid watermarks in facial contours, eliminating the need for prior knowledge of swapping techniques or large-scale message storage.

Findings

Outperforms state-of-the-art detectors across 8 face swapping methods.

Balances image quality with watermark robustness effectively.

Does not require training on specific face swapping techniques.

Abstract

Face swapping, recognized as a privacy and security concern, has prompted considerable defensive research. With the advancements in AI-generated content, the discrepancies between the real and swapped faces have become nuanced. Considering the difficulty of forged traces detection, we shift the focus to the face swapping purpose and proactively embed elaborate watermarks against unknown face swapping techniques. Given that the constant purpose is to swap the original face identity while preserving the background, we concentrate on the regions surrounding the face to ensure robust watermark generation, while embedding the contour texture and face identity information to achieve progressive image determination. The watermark is located in the facial contour and contains hybrid messages, dubbed the contour-hybrid watermark (CMark). Our approach generalizes face swapping detection without requiring any swapping techniques during training and the storage of large-scale messages in advance. Experiments conducted across 8 face swapping techniques demonstrate the superiority of our approach compared with state-of-the-art passive and proactive detectors while achieving a favorable balance between the image quality and watermark robustness.