Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand
Junfeng Guo, Yiming Li, Lixu Wang, Shu-Tao Xia, Heng Huang, Cong Liu, Bo Li
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 domain watermark instead of backdoor watermarks | dataset ownership verification · CIFAR-10 | harmful degree H: 1.00 -> 0.10 (vs BadNets) | Improved |
| use domain watermark instead of clean-label backdoor watermarks | dataset ownership verification · Tiny-ImageNet | benign accuracy (%): 51.79 -> 59.10 (vs UBW-C) | Improved |
| use domain watermark instead of backdoor watermarks | dataset ownership verification · Tiny-ImageNet | verification success rate (%): 58.06 vs 100 (BadNets) | Hurt |
| increase perturbation budget epsilon (ablation) | domain watermark · CIFAR-10 and Tiny-ImageNet | verification success rate | Improved |
| increase watermarking rate gamma (ablation) | domain watermark · CIFAR-10 and Tiny-ImageNet | verification success rate | Improved |
| increase perturbation budget epsilon (ablation) | domain watermark · CIFAR-10 and Tiny-ImageNet | benign accuracy | No clear effect |
| fine-tune the watermarked model | domain watermark · CIFAR-10 | VSR and BA | No clear effect |
Closest papers by meaning
- ZeroMark: Towards Dataset Ownership Verification without Disclosing Watermark (NeurIPS 2024 · similarity 0.95)
- EntropyMark: Towards More Harmless Backdoor Watermark via Entropy-based Constraint for Open-source Dataset Copyright Protection (CVPR 2025 · similarity 0.93)
- Safe and Robust Watermark Injection with a Single OoD Image (ICLR 2024 · similarity 0.88)
- Lightweight-Mark: Rethinking Deep Learning-Based Watermarking (ICML 2025 · similarity 0.88)
- Disentangled Style Domain for Implicit $z$-Watermark Towards Copyright Protection (NeurIPS 2024 · similarity 0.87)
- Data Taggants: Dataset Ownership Verification Via Harmless Targeted Data Poisoning (ICLR 2025 · similarity 0.87)
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.
