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

arXiv: https://arxiv.org/abs/2605.01479 · HTML: https://mlsanity.com/paper/2605.01479/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 6 of its 41 references that are in the map.
- First posted on arXiv 2 May 2026.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)
- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 6 of 6)

- [Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models](https://mlsanity.com/paper/2510.20468/) (2025)
- [WMCopier: Forging Invisible Image Watermarks on Arbitrary Images](https://mlsanity.com/paper/2503.22330/) (2025)
- [Attack-Resistant Watermarking for AIGC Image Forensics via Diffusion-based Semantic Deflection](https://mlsanity.com/paper/2601.06639/) (2026)
- [TraceMark-LDM: Authenticatable Watermarking for Latent Diffusion Models via Binary-Guided Rearrangement](https://mlsanity.com/paper/2503.23332/) (2025)
- [Efficient and Accurate Image Provenance Analysis: A Scalable Pipeline for Large-scale Images](https://mlsanity.com/paper/2506.23707/) (2025)
- [Untraceable DeepFakes via Traceable Fingerprint Elimination](https://mlsanity.com/paper/2508.03067/) (2025)

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

- [Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle](https://mlsanity.com/paper/2608.04314/) (2026)
- [Residual Transferability in Neural Image Watermarking](https://mlsanity.com/paper/2609.32241/) (2026)

## Abstract (arXiv)

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.