Research map / Image generation / Text-to-image diffusion
Who Controls the Authorization? Invertible Networks for Copyright Protection in Text-to-Image Synthesis
Baoyue Hu, Yang Wei, Junhao Xiao, Wendong Huang, Xiuli Bi, Bin Xiao
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 contrastive learning-based adversarial loss Ladvc (ablation) | Ours · VGGFace2 (20 identities) | FID: 214.22 -> 324.11 | Improved |
| add contrastive learning-based adversarial loss Ladvc (ablation) | Ours · VGGFace2 (20 identities) | PSNR: 36.1336 -> 30.7634 | Hurt |
| add DWT frequency-domain processing (ablation) | Ours · VGGFace2 (20 identities) | FID: 317.35 -> 324.11 | Improved |
| add DWT frequency-domain processing (ablation) | Ours · VGGFace2 (20 identities) | PSNR: 28.9580 -> 30.7634 | Improved |
| add compound coupling module (ablation) | Ours · VGGFace2 (20 identities) | FID: 314.10 -> 324.11 | Improved |
| apply JPEG compression purification to copyrighted images | Ours · VGGFace2 | FID: 300.35 -> 300.59 | No clear effect |
| apply super-resolution purification to copyrighted images | Ours · VGGFace2 | FID: 300.35 -> 306.11 | No clear effect |
| apply Gaussian filtering purification to copyrighted images | Ours · VGGFace2 | FID: 300.35 -> 175.76 | Hurt |
| use unseen prompt (dslr portrait) instead of training prompt | Ours · VGGFace2 | FID: 300.35 -> 314.71 | Improved |
| use unseen prompt instead of training prompt | MetaCloak · VGGFace2 | FID: 193.17 -> 154.89 | Hurt |
| use Ours instead of ASPL on facial identity disruption | Ours · VGGFace2 | ISM: 0.3208 -> 0.4611 | Hurt |
| use Ours instead of Wm-AdvDM | Ours · VGGFace2 | FID: 160.12 -> 300.35 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- MetaCloak — MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning (CVPR 2024) · better on 2 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models (CVPR 2024 · similarity 0.89)
- Countering Personalized Text-to-Image Generation with Influence Watermarks (CVPR 2024 · similarity 0.87)
- Disentangled Style Domain for Implicit $z$-Watermark Towards Copyright Protection (NeurIPS 2024 · similarity 0.87)
- Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion? (CVPR 2024 · similarity 0.85)
- IWRN:A Robust Blind Watermarking Method for Artwork Image Copyright Protection Against Noise Attack (AAAI 2025 · similarity 0.85)
- Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models (NeurIPS 2025 · 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.
