Hide and Seek: How Does Watermarking Impact Face Recognition?

arXiv:2404.18890v1 Announce Type: new
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 …

abstract accuracy arxiv augmentation challenges cs.cv data data privacy development face face recognition generative generative models hide however images impact novel privacy progress recognition seek synthesis training training data type watermarking