mlsanityData to 14 Oct 2026

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

arXiv 2603.01067 ↗First posted 1 Mar 2026cs.CR cs.AIcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper 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

17 of 37 references.

References · 17

  1. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 504
  2. 2019Face X-ray for More General Face Forgery Detectioncited by 470
  3. 2018HiDDeN: Hiding Data With Deep Networkscited by 397
  4. 2021Multi-attentional Deepfake Detectioncited by 341
  5. 2023GenImage: A Million-Scale Benchmark for Detecting AI-Generated Imagecited by 321
  6. 2019StegaStamp: Invisible Hyperlinks in Physical Photographscited by 265
  7. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 201
  8. 2019Adversarial Training and Robustness for Multiple Perturbationscited by 183
  9. 2024Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Modelscited by 142
  10. 2020Responsible Disclosure of Generative Models Using Scalable Fingerprintingcited by 91
  11. 2022How Mask Matters: Towards Theoretical Understandings of Masked Autoencoderscited by 86
  12. 2023Robust Evaluation of Diffusion-Based Adversarial Purificationcited by 65
5 more
  1. 2023Leveraging Optimization for Adaptive Attacks on Image Watermarkscited by 52
  2. 2023PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generatorscited by 37
  3. 2024UnMarker: A Universal Attack on Defensive Image Watermarkingcited by 24
  4. 2022Making DeepFakes more spurious: evading deep face forgery detection via trace removal attackcited by 16
  5. 2025HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaignscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026CSC: Turning the Adversary's Poison against Itselfcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Removing the Watermark Is Not Enough: Forensic Stealth in Generative-AI Watermark Removal
  2. 2025A Baseline Method for Removing Invisible Image Watermarks using Deep Image Prior
  3. 2023Invisible Image Watermarks Are Provably Removable Using Generative AI
  4. 2026Watermarks Attack Watermarks: Re-Watermarking as a Generic Removal Strategy
  5. 2026Where Does the Watermark Hide? Push-Pull Disentanglement for Invisible Watermark Removal
  6. 2024Spy-Watermark: Robust Invisible Watermarking for Backdoor Attack
  7. 2026RAVEN: Erasing Invisible Watermarks via Novel View Synthesis
  8. 2026Vanishing Watermarks: Diffusion-Based Image Editing Undermines Robust Invisible Watermarking