GenPTW: Latent Image Watermarking for Provenance Tracing and Tamper Localization

TL;DR

GenPTW is proposed, a watermarking framework that unifies provenance tracing and tamper localization in latent space and is plug-and-play compatible with latent diffusion models (LDMs) and visual autoregressive (VAR) models.

Abstract

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.

Figures (6)

• Figure 1: The process of embedding and extracting GenPTW for dual forensic objectives.
• Figure 2: The Framework of GenPTW. A Wm plug-in inserted during generation without modifying the original model.
• Figure 3: Illustration of Cross-Attention Fusion Block.
• Figure 4: Average attention maps during image generation with the watermark module.
• Figure 5: Qualitative examples of generated images using GenPTW.