CSGuard: Toward Forgery-Resistant Watermarking in Diffusion Models via Compressed Sensing Constraint

TL;DR

CSGuard introduces a compressed sensing-based watermarking method for diffusion models that significantly enhances forgery resistance while maintaining watermark integrity and detection accuracy.

Contribution

It is the first to propose a forgery-resistant watermarking scheme using compressed sensing with a secret matrix for diffusion models.

Findings

Reduces forgery attack success rate from 100% to 28.12%.

Achieves 100% detection rate on benign watermarked images.

Maintains watermarking effectiveness without quality loss.

Abstract

Latent-based diffusion model watermarking embeds watermarks into generated images' latent space to enable content attribution, offering a training-free solution for intellectual property protection and digital forensics. However, these methods exhibit a critical vulnerability to the forgery attack, attackers can extract the watermark by inverting the watermarked image and re-generating it with an arbitrary prompt, thereby enabling false attribution on malicious content. In this paper, we propose the CSGuard, the first forgery-resistant watermarking schema that leverages compressed sensing to bind the watermarked image generation and verification to a secret matrix. This ensures that only users possessing the secret matrix can correctly embed or verify the image watermark, prevents the illegal users from forgery without compromising generation quality and watermark integrity. Experimental results demonstrate that CSGuard achieves strong forgery resistance, reduces the attack success rate from 100.0\% to 28.12\%, and achieve 100\% detection rate on benign watermarked images without compromising watermarking effectiveness.