Watermark Removal

Ask about this topic

Overview

Watermark removal studies how edits can erase or weaken embedded signals used to identify generated or copyrighted content across text, images, and audio. Approaches include paraphrasing and rewriting, image reconstruction and frequency or latent-space manipulation, diffusion-based regeneration, and speech enhancement. Evaluations measure whether detectors still recognize the mark alongside content quality, semantic preservation, and whether forensic methods can detect the removal itself. The central tension is that attacks aim to remove marks with minimal damage, while stronger watermarks must withstand diverse edits without degrading the content they protect.

Latest papers

CardsList

40 papers7 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

  1. Breaking Watermarks in the Frequency Domain: A Modulated Diffusion Attack Framework

    Apr 24, 2026Chunpeng Wang, Binyan Qu, Xiaoyu Wang +4Watermark RemovalDiffusion Models

    Qilu University of Technology (Shandong Academy of Sciences) Jinan, Shandong Province, China · Dalian Maritime University Dalian, Liaoning Province, China · Nanjing University of Science and Technology Nanjing, Jiangsu Province, China +1

  2. On the Robustness of Watermarking for Autoregressive Image Generation

    Apr 13, 2026Andreas Müller, Denis Lukovnikov, Shingo Kodama +5Watermark RemovalRobust Watermarking

    Ruhr University Bochum · Middlebury College · New York University +2

  3. Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Models

    Apr 13, 2026Shuhao Zhang, Yuli Chen, Jiale Han +2Adversarial Attacks on LLMsLLM Watermarking

    State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications · Hong Kong University of Science and Technology

  4. Towards Robust Content Watermarking Against Removal and Forgery Attacks

    Apr 8, 2026Yifan Zhu, Yihan Wang, Xiao-Shan GaoRobust WatermarkingDiffusion Model Watermarking

    Academy of Mathematics and Systems Science, Chinese Academy of Sciences and University of Chinese Academy of Sciences. · University of Waterloo

  5. ResGuard: Enhancing Robustness Against Known Original Attacks in Deep Watermarking

    Apr 4, 2026Hanyi Wang, Han Fang, Yupeng Qiu +2Robust WatermarkingWatermark Removal

    Shanghai Jiao Tong University China · University of Science and Technology of China China · National University of Singapore Singapore

  6. SHIFT: Stochastic Hidden-Trajectory Deflection for Removing Diffusion-based Watermark

    Mar 31, 2026Rui Bao, Zheng Gao, Xiaoyu Li +3Watermark RemovalDiffusion Model Watermarking

    University of New South Wales · Griffith University

  7. The Orthogonal Vulnerabilities of Generative AI Watermarks: A Comparative Empirical Benchmark of Spatial and Latent Provenance

    Mar 11, 2026Jesse Yu, Nicholas WeiAI-Generated Image WatermarkingRobust Watermarking

    Millburn High School · Williamsville East High School

  8. On Google's SynthID-Text LLM Watermarking System: Theoretical Analysis and Empirical Validation

    Mar 3, 2026Romina Omidi, Yun Dong, Binghui WangLLM WatermarkingRobust Watermarking

    Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA

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

    Mar 1, 2026Huajie Chen, Tianqing Zhu, Hailin Yang +7Watermark RemovalAI-Generated Image Watermarking

    City University of Macau · CISPA Helmholtz Center for Information Security · Guangzhou University

  10. Breaking Semantic-Aware Watermarks via LLM-Guided Coherence-Preserving Semantic Injection

    Feb 25, 2026Zheng Gao, Xiaoyu Li, Zhicheng Bao +2Watermark RemovalDiffusion Model Watermarking

    University of New South Wales Sydney, New South Wales, Australia · Griffith University Brisbane, Queensland, Australia