Salvato in:
Dettagli Bibliografici
Autori principali: Gan, Zhenliang, Liu, Chunya, Tang, Yichao, Wang, Binghao, Cui, Shiwen, Wang, Weiqiang, Zhang, Xinpeng
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2504.19567
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914267557527552
author Gan, Zhenliang
Liu, Chunya
Tang, Yichao
Wang, Binghao
Cui, Shiwen
Wang, Weiqiang
Zhang, Xinpeng
author_facet Gan, Zhenliang
Liu, Chunya
Tang, Yichao
Wang, Binghao
Cui, Shiwen
Wang, Weiqiang
Zhang, Xinpeng
contents The proliferation of generative image models has revolutionized AIGC creation while amplifying concerns over content provenance and manipulation forensics. Existing methods are typically either unable to localize tampering or restricted to specific generative settings, limiting their practical utility. We propose \textbf{GenPTW}, a \textbf{Gen}eral watermarking framework that unifies \textbf{P}rovenance tracing and \textbf{T}amper localization in latent space. It supports both in-generation and post-generation embedding without altering the generative process, and is plug-and-play compatible with latent diffusion models (LDMs) and visual autoregressive (VAR) models. To achieve precise provenance tracing and tamper localization, we embed the watermark using two complementary mechanisms: cross-attention fusion aligned with latent semantics and spatial fusion providing explicit spatial guidance for edit sensitivity. A tamper-aware extractor jointly conducts provenance tracing and tamper localization by leveraging watermark features together with high-frequency features. Experiments show that GenPTW maintains high visual fidelity and strong robustness against diverse AIGC-editing.
format Preprint
id arxiv_https___arxiv_org_abs_2504_19567
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GenPTW: Latent Image Watermarking for Provenance Tracing and Tamper Localization
Gan, Zhenliang
Liu, Chunya
Tang, Yichao
Wang, Binghao
Cui, Shiwen
Wang, Weiqiang
Zhang, Xinpeng
Cryptography and Security
The proliferation of generative image models has revolutionized AIGC creation while amplifying concerns over content provenance and manipulation forensics. Existing methods are typically either unable to localize tampering or restricted to specific generative settings, limiting their practical utility. We propose \textbf{GenPTW}, a \textbf{Gen}eral watermarking framework that unifies \textbf{P}rovenance tracing and \textbf{T}amper localization in latent space. It supports both in-generation and post-generation embedding without altering the generative process, and is plug-and-play compatible with latent diffusion models (LDMs) and visual autoregressive (VAR) models. To achieve precise provenance tracing and tamper localization, we embed the watermark using two complementary mechanisms: cross-attention fusion aligned with latent semantics and spatial fusion providing explicit spatial guidance for edit sensitivity. A tamper-aware extractor jointly conducts provenance tracing and tamper localization by leveraging watermark features together with high-frequency features. Experiments show that GenPTW maintains high visual fidelity and strong robustness against diverse AIGC-editing.
title GenPTW: Latent Image Watermarking for Provenance Tracing and Tamper Localization
topic Cryptography and Security
url https://arxiv.org/abs/2504.19567