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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xia, Ruiyang, Zhou, Dawei, Liu, Decheng, Yuan, Lin, Li, Jie, Wang, Nannan, Gao, Xinbo
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915307087462400
author Xia, Ruiyang
Zhou, Dawei
Liu, Decheng
Yuan, Lin
Li, Jie
Wang, Nannan
Gao, Xinbo
author_facet Xia, Ruiyang
Zhou, Dawei
Liu, Decheng
Yuan, Lin
Li, Jie
Wang, Nannan
Gao, Xinbo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19081
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Generalized Proactive Defense against Face Swapping with Contour-Hybrid Watermark
Xia, Ruiyang
Zhou, Dawei
Liu, Decheng
Yuan, Lin
Li, Jie
Wang, Nannan
Gao, Xinbo
Computer Vision and Pattern Recognition
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.
title Towards Generalized Proactive Defense against Face Swapping with Contour-Hybrid Watermark
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.19081