Research map / Image generation / Editing and style transfer
StyleSentinel: Reliable Artistic Copyright Verification via Stylistic Fingerprints
Lingxiao Chen, Liqin Wang, Wei Lu
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 |
|---|---|---|---|
| add semantic self-reconstruction style augmentation (ablation) | StyleSentinel · SD1.5 (WikiArt) | TPR@FPR=1e-2: 0.659 -> 0.938 | Improved |
| semantic self-reconstruction instead of traditional augmentation (ablation) | StyleSentinel · SD1.5 (WikiArt) | TPR@FPR=1e-2: 0.791 -> 0.938 | Improved |
| attentional fusion instead of concatenation (ablation) | StyleSentinel · SD2.1 (WikiArt) | TPR@FPR=1e-2: 0.741 -> 0.953 | Improved |
| hypersphere one-class verifier instead of BCE classifier (ablation) | StyleSentinel · SD1.5 (WikiArt) | TPR@FPR=1e-2: 0.838 -> 0.938 | Improved |
| add augmentation, effect on AUC (ablation) | StyleSentinel · SD1.5 (WikiArt) | AUC: 0.975 -> 0.994 | Improved |
| StyleSentinel vs ArtistAuditor | fingerprint verification · WikiArt SD1.5 DreamBooth | TPR@FPR=1e-2: 0.626 -> 0.928 | Improved |
| StyleSentinel vs ArtistAuditor on lower-resolution data | fingerprint verification · ArtBench SD1.5 DreamBooth | TPR@FPR=1e-2: 0.470 -> 0.901 | Improved |
| color-space alterations of suspect images | StyleSentinel · SD1.5/SD2.1 | TPR@FPR=1e-2 | Mixed |
| unbalanced loss weights (lambda_pos != lambda_neg) (ablation) | StyleSentinel · WikiArt | AUC and TPR | Hurt |
Closest papers by meaning
- Rethinking Artistic Copyright Infringements In the Era Of Text-to-Image Generative Models (ICLR 2025 · similarity 0.88)
- SigStyle: Signature Style Transfer via Personalized Text-to-Image Models (AAAI 2025 · similarity 0.86)
- Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI (ICLR 2025 · similarity 0.86)
- Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models (NeurIPS 2024 · similarity 0.86)
- ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bank (AAAI 2024 · similarity 0.85)
- Disentangled Style Domain for Implicit $z$-Watermark Towards Copyright Protection (NeurIPS 2024 · similarity 0.85)
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.
