Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ma, Rui, Guo, Mengxi, Yuming, Li, Zhang, Hengyuan, Ma, Cong, Li, Yuan, Xie, Xiaodong, Zhang, Shanghang
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2403.12053
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910374625804288
author Ma, Rui
Guo, Mengxi
Yuming, Li
Zhang, Hengyuan
Ma, Cong
Li, Yuan
Xie, Xiaodong
Zhang, Shanghang
author_facet Ma, Rui
Guo, Mengxi
Yuming, Li
Zhang, Hengyuan
Ma, Cong
Li, Yuan
Xie, Xiaodong
Zhang, Shanghang
contents Integrating watermarks into generative images is a critical strategy for protecting intellectual property and enhancing artificial intelligence security. This paper proposes Plug-in Generative Watermarking (PiGW) as a general framework for integrating watermarks into generative images. More specifically, PiGW embeds watermark information into the initial noise using a learnable watermark embedding network and an adaptive frequency spectrum mask. Furthermore, it optimizes training costs by gradually increasing timesteps. Extensive experiments demonstrate that PiGW enables embedding watermarks into the generated image with negligible quality loss while achieving true invisibility and high resistance to noise attacks. Moreover, PiGW can serve as a plugin for various commonly used generative structures and multimodal generative content types. Finally, we demonstrate how PiGW can also be utilized for detecting generated images, contributing to the promotion of secure AI development. The project code will be made available on GitHub.
format Preprint
id arxiv_https___arxiv_org_abs_2403_12053
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PiGW: A Plug-in Generative Watermarking Framework
Ma, Rui
Guo, Mengxi
Yuming, Li
Zhang, Hengyuan
Ma, Cong
Li, Yuan
Xie, Xiaodong
Zhang, Shanghang
Multimedia
Integrating watermarks into generative images is a critical strategy for protecting intellectual property and enhancing artificial intelligence security. This paper proposes Plug-in Generative Watermarking (PiGW) as a general framework for integrating watermarks into generative images. More specifically, PiGW embeds watermark information into the initial noise using a learnable watermark embedding network and an adaptive frequency spectrum mask. Furthermore, it optimizes training costs by gradually increasing timesteps. Extensive experiments demonstrate that PiGW enables embedding watermarks into the generated image with negligible quality loss while achieving true invisibility and high resistance to noise attacks. Moreover, PiGW can serve as a plugin for various commonly used generative structures and multimodal generative content types. Finally, we demonstrate how PiGW can also be utilized for detecting generated images, contributing to the promotion of secure AI development. The project code will be made available on GitHub.
title PiGW: A Plug-in Generative Watermarking Framework
topic Multimedia
url https://arxiv.org/abs/2403.12053