GenPTW: Latent Image Watermarking for Provenance Tracing and Tamper Localization
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (5) · 4085-4093
DOI: 10.1609/aaai.v40i5.37412 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhenliang Gan und 6 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).
Abstract (Originalsprache)
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 GenPTW, a General watermarking framework that unifies Provenance tracing and Tamper 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.
Zitieren
APA
Gan, Z., Liu, C., Tang, Y., Wang, B., Cui, S., Wang, W., & Zhang, X. (2026). GenPTW: Latent Image Watermarking for Provenance Tracing and Tamper Localization. Proceedings of the AAAI Conference on Artificial Intelligence, 40(5), 4085-4093. https://doi.org/10.1609/aaai.v40i5.37412
Vancouver
Gan Z, Liu C, Tang Y, Wang B, Cui S, Wang W, et al. GenPTW: Latent Image Watermarking for Provenance Tracing and Tamper Localization. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(5):4085-4093. doi:10.1609/aaai.v40i5.37412
BibTeX
@article{Gan2026,
author = {Gan, Zhenliang and Liu, Chunya and Tang, Yichao and Wang, Binghao and Cui, Shiwen and Wang, Weiqiang and Zhang, Xinpeng},
title = {GenPTW: Latent Image Watermarking for Provenance Tracing and Tamper Localization},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {5},
pages = {4085--4093},
doi = {10.1609/aaai.v40i5.37412}
}
EUVIMED