# Hide&Seek: Remove Image Watermarks with Negligible Cost via Pixel-wise Reconstruction

arXiv: https://arxiv.org/abs/2603.01067 · HTML: https://mlsanity.com/paper/2603.01067/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 37 references that are in the map.
- First posted on arXiv 1 Mar 2026.

## Builds on (most cited first, 17 of 17)

- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)
- [Face X-ray for More General Face Forgery Detection](https://mlsanity.com/paper/1912.13458/) (2019)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [Multi-attentional Deepfake Detection](https://mlsanity.com/paper/2103.02406/) (2021)
- [GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image](https://mlsanity.com/paper/2306.08571/) (2023)
- [StegaStamp: Invisible Hyperlinks in Physical Photographs](https://mlsanity.com/paper/1904.05343/) (2019)
- [Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data](https://mlsanity.com/paper/2007.08457/) (2020)
- [Adversarial Training and Robustness for Multiple Perturbations](https://mlsanity.com/paper/1904.13000/) (2019)
- [Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models](https://mlsanity.com/paper/2404.04956/) (2024)
- [Responsible Disclosure of Generative Models Using Scalable Fingerprinting](https://mlsanity.com/paper/2012.08726/) (2020)
- [How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders](https://mlsanity.com/paper/2210.08344/) (2022)
- [Robust Evaluation of Diffusion-Based Adversarial Purification](https://mlsanity.com/paper/2303.09051/) (2023)
- [Leveraging Optimization for Adaptive Attacks on Image Watermarks](https://mlsanity.com/paper/2309.16952/) (2023)
- [PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators](https://mlsanity.com/paper/2304.07361/) (2023)
- [UnMarker: A Universal Attack on Defensive Image Watermarking](https://mlsanity.com/paper/2405.08363/) (2024)
- [Making DeepFakes more spurious: evading deep face forgery detection via trace removal attack](https://mlsanity.com/paper/2203.11433/) (2022)
- [HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns](https://mlsanity.com/paper/2501.16750/) (2025)

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

- [CSC: Turning the Adversary's Poison against Itself](https://mlsanity.com/paper/2604.21416/) (2026)

## Abstract (arXiv)

Watermarking has emerged as a key defense against the misuse of machine-generated images (MGIs). Yet the robustness of these protections remains underexplored. To reveal the limits of SOTA proactive image watermarking defenses, we propose HIDE&SEEK (HS), a suite of versatile and cost-effective attacks that reliably remove embedded watermarks while preserving high visual fidelity.