What Breaks Local Watermarks? A Robustness Benchmark for Local Invisible Image Watermarking
First systematic robustness benchmark of five local invisible image watermarking methods across 55 transformations finds all are vulnerable, with inpainting and geometric misalignment completely breaking payload…
The paper presents the first systematic robustness benchmark for local invisible image watermarks, covering 55 image transformations across signal distortions, coordinate alignment changes, indirect local edits, and direct watermark edits. It evaluates five methods: MaskWM, WAM, OmniGuard, TrustMark, and PixelSeal, all supporting localization natively or with minimal adaptation. Results show every method is vulnerable to some transformation; MaskWM offers the strongest payload recovery and localization but the lowest clean-image quality, and synchronization further improves its recovery under geometric transformations. Geometric misalignment and generative local edits such as inpainting and outpainting can completely impair payload recovery, while signal distortions are often tolerated.
- First robustness benchmark for local image watermarks spanning 55 transformations
- Evaluates MaskWM, WAM, OmniGuard, TrustMark, and PixelSeal
- All evaluated methods are vulnerable to at least one transformation
- Inpainting, outpainting, and geometric misalignment can completely break payload recovery
- MaskWM strongest on recovery and localization despite lowest clean image quality
From the original article
1 min read at arxiv.orgLocal image watermarking embeds an invisible signal into selected image regions rather than spreading it across the entire image, enabling payload recovery from specific objects or regions without perceptibly altering the image.
By Kai Yao · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.