# GenPTW: Latent Image Watermarking for Provenance Tracing and Tamper Localization

arXiv: https://arxiv.org/abs/2504.19567 · HTML: https://mlsanity.com/paper/2504.19567/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2025.

## Built on by (most cited first, 2 of 2)

- [SimuFreeMark: A Noise-Simulation-Free Robust Watermarking Against Image Editing](https://mlsanity.com/paper/2511.11295/) (2025)
- [Trustworthy synthetic visual media: Evidence across the media lifecycle](https://mlsanity.com/paper/2609.34232/) (2026)

## Abstract (arXiv)

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.