Research map / Adversarial robustness and security / Certified and empirical robustness
Certifiably Robust Image Watermark
Zhengyuan Jiang, Moyang Guo, Yuepeng Hu, Jinyuan Jia, Neil Zhenqiang Gong
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use regression smoothing instead of multi-class or multi-label smoothing (ablation) | smoothed watermarking · Stable Diffusion, certified robustness | CFNR and CFPR | Improved |
| train the base watermark encoder/decoder with Gaussian-noise adversarial training instead of standard training (ablation) | regression smoothing watermark · Stable Diffusion, certified robustness | CFNR and CFPR: SSIM 0.943 vs 0.941 (similar quality) | Improved |
| lower the detection threshold tau (ablation) | regression smoothing watermark · Stable Diffusion, certified robustness | CFNR and CFPR | Mixed |
| set smoothing noise sigma too small or too large (ablation) | regression smoothing watermark · Stable Diffusion, certified robustness | CFNR and CFPR | Hurt |
| apply randomized smoothing to the watermark decoder | HiDDeN base watermark · JPEG compression removal attack | FNR: 0.25 -> close to 0 | Improved |
| apply randomized smoothing to the watermark decoder | HiDDeN base watermark · black-box removal/forgery attack | perturbation size at given query budget | Improved |
Closest papers by meaning
- An Undetectable Watermark for Generative Image Models (ICLR 2025 · similarity 0.91)
- Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks (ICLR 2024 · similarity 0.90)
- On the Robustness of Watermarking for Autoregressive Image Generation (NeurIPS 2026 · similarity 0.89)
- RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees (NeurIPS 2024 · similarity 0.89)
- ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization (NeurIPS 2024 · similarity 0.88)
- Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances (ICLR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
