Abstract
This paper presents an attack method on the StegaStamp watermarking algorithm that completely removes watermarks from an image with minimal quality loss, developed as part of the NeurIPS "Erasing the invisible" competition.
Watermark Overwriting Attack on StegaStamp algorithm
Related papers
Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).
- Watermarks Attack Watermarks: Re-Watermarking as a Generic Removal Strategy (2026)67% match
- Removing Watermarks with Partial Regeneration using Semantic Information (2025)67% match
- MarkSweep: A No-box Removal Attack on AI-Generated Image Watermarking via Noise Intensification and Frequency-aware Denoising (2026)66% match
- Invisible Image Watermarks Are Provably Removable Using Generative AI (2023)66% match
- Removal Attack and Defense on AI-generated Content Latent-based Watermarking (2025)65% match
- Leveraging Optimization for Adaptive Attacks on Image Watermarks (2023)65% match
- High-frequency Matters: An Overwriting Attack and defense for Image-processing Neural Network Watermarking (2023)64% match
- Hide&Seek: Remove Image Watermarks with Negligible Cost via Pixel-wise Reconstruction (2026)64% match