# The Forensic Cost of Watermark Removal: From Dedicated Attacks to Image Editing

arXiv: https://arxiv.org/abs/2604.25491 · HTML: https://mlsanity.com/paper/2604.25491/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 43 references that are in the map.
- First posted on arXiv 28 Apr 2026.

## Builds on (most cited first, 29 of 29)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks](https://mlsanity.com/paper/1704.01155/) (2017)
- [Diffusion Models for Adversarial Purification](https://mlsanity.com/paper/2205.07460/) (2022)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [DIRE for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2303.09295/) (2023)
- [The Stable Signature: Rooting Watermarks in Latent Diffusion Models](https://mlsanity.com/paper/2303.15435/) (2023)
- [On the detection of synthetic images generated by diffusion models](https://mlsanity.com/paper/2211.00680/) (2022)
- [AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error](https://mlsanity.com/paper/2401.17879/) (2024)
- [EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection](https://mlsanity.com/paper/2312.08883/) (2023)
- [MBRS : Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compression](https://mlsanity.com/paper/2108.08211/) (2021)
- [Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances](https://mlsanity.com/paper/2410.18775/) (2024)
- [WAVES: Benchmarking the Robustness of Image Watermarks](https://mlsanity.com/paper/2401.08573/) (2024)
- [Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models](https://mlsanity.com/paper/2311.04378/) (2023)
- [Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms](https://mlsanity.com/paper/2212.12678/) (2022)
- [SurFree: a fast surrogate-free black-box attack](https://mlsanity.com/paper/2011.12807/) (2020)
- [Image Watermarks are Removable Using Controllable Regeneration from Clean Noise](https://mlsanity.com/paper/2410.05470/) (2024)
- [Video Seal: Open and Efficient Video Watermarking](https://mlsanity.com/paper/2412.09492/) (2024)
- [FireRed-Image-Edit-1.0 Technical Report](https://mlsanity.com/paper/2602.13344/) (2026)
- [Detecting Adversarial Examples by Input Transformations, Defense Perturbations, and Voting](https://mlsanity.com/paper/2101.11466/) (2021)
- [Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models](https://mlsanity.com/paper/2510.20468/) (2025)
- [SWIFT: Semantic Watermarking for Image Forgery Thwarting](https://mlsanity.com/paper/2407.18995/) (2024)
- [We Can Hide More Bits: The Unused Watermarking Capacity in Theory and in Practice](https://mlsanity.com/paper/2510.12812/) (2025)
- [Fast, Secure, and High-Capacity Image Watermarking with Autoencoded Text Vectors](https://mlsanity.com/paper/2510.00799/) (2025)

## Built on by (most cited first, 1 of 1)

- [Removing the Watermark Is Not Enough: Forensic Stealth in Generative-AI Watermark Removal](https://mlsanity.com/paper/2605.09203/) (2026)

## Abstract (arXiv)

Current watermark removal methods are evaluated on two axes: attack success rate and perceptual quality. We show this is insufficient. While state-of-the-art attacks successfully degrade the watermark signal without visible distortion, they leave distinct statistical artifacts that betray the removal attempt. We name this overlooked axis Watermark Removal Detection (WRD) and demonstrate that a modern classifier trained on these artifacts achieves state-of-the-art detection rates at 10-3 FPR across every removal method tested. No existing attack accounts for this forensic leakage. We benchmark leading watermarking schemes against standard removal pipelines under the extended evaluation triple of attack success, perceptual quality, and forensic detectability, and find that no current method balances all three. Our results establish forensic stealthiness as a necessary requirement for watermark removal.