Research map / Image generation / Editing and style transfer
Protecting Celebrities From DeepFake With Identity Consistency Transformer
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 reference-assisted identity matching to ICT | ICT · Celeb-DF v2 | frame-level AUC (%): 85.71 -> 94.43 | Helped |
| Add the consistency loss (ablation) | ICT · Celeb-DF v2 | frame-level AUC (%): 51.48 -> 85.71 | Helped |
| Add mask deformation during training data generation (ablation) | ICT · Celeb-DF v2 | frame-level AUC (%): 83.44 -> 85.71 | Helped |
| Add color correction during training data generation (ablation) | ICT · Celeb-DF v2 | frame-level AUC (%): 82.86 -> 85.71 | Helped |
| Use D_in alone rather than D_in_out (ablation) | ICT · Celeb-DF v2 | AUC (%): 85.71% -> 92.52% | Helped |
| Use D_out alone rather than D_in_out (ablation) | ICT · Celeb-DF v2 | AUC (%): 85.71% -> 87.45% | Helped |
| Combine the reference-assisted measures as D_ref (ablation) | ICT · Celeb-DF v2 | AUC (%): 85.71% -> 94.43% | Helped |
| Replace the Transformer with a split-image ResNet50 (ablation) | ICT · Deeper | frame-level AUC (%): 93.57 -> 79.42 | Hurt |
| Replace the Transformer with separate ResNet50 models (ablation) | ICT · Deeper | frame-level AUC (%): 93.57 -> 91.48 | Hurt |
| Use fewer reference images per identity or drop more identities (ablation) | ICT-Ref · Celeb-DF v2 | frame-level AUC | Mixed |
| Apply stronger image degradation | ICT · degraded images | frame-level AUC | Mixed |
Closest papers by meaning
- Identity-Aware Vision-Language Model for Explainable Face Forgery Detection (AAAI 2026 · similarity 0.87)
- Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes (NeurIPS 2025 · similarity 0.87)
- FakeDiffer: Distributional Disparity Learning on Differentiated Reconstruction for Face Forgery Detection (AAAI 2025 · similarity 0.86)
- From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakes (NeurIPS 2025 · similarity 0.85)
- Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector (CVPR 2025 · similarity 0.84)
- Disguise without Disruption: Utility-Preserving Face De-identification (AAAI 2024 · similarity 0.84)
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.