Research map / Image generation / Editing and style transfer
FaceTracer: Unveiling Source Identities From Swapped Face Images and Videos for Fraud Prevention
Zhongyi Zhang, Jie Zhang, Wenbo Zhou, Xinghui Zhou, Qing Guo, Weiming Zhang, Tianwei Zhang, Nenghai Yu
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 FaceTracer source-identity extractor instead of ArcFace baseline | ArcFace ResNet18 · HiRes swapped faces (S1) | Top-1 accuracy (%): 0.04 -> 98.80 | Improved |
| add reference images during training (S2 vs S3) | FaceTracer · HiRes swapped faces | Top-1 accuracy (%): 93.34 -> 99.27 | Improved |
| add reference images during training (S2 vs S3) | FaceTracer · InfoSwap swapped faces | Top-1 accuracy (%): 91.83 -> 98.19 | Improved |
| add reference images at inference (S1 vs S2) | FaceTracer · HiRes swapped faces | Top-1 accuracy (%): 99.27 -> 98.80 | No clear effect |
| use ViT-S backbone instead of ResNet18 (ablation) | FaceTracer · HiRes swapped faces (S1) | Top-1 accuracy (%): 78.71 -> 98.80 | Improved |
| use ViT-S backbone instead of ResNet18 (ablation) | FaceTracer · FaceShifter swapped faces (S1) | Top-1 accuracy (%): 99.25 -> 99.40 | No clear effect |
| use explicit disentanglement instead of cross-attention (ablation) | FaceTracer · HiRes swapped faces (S1) | Top-1 accuracy (%): 97.56 -> 98.80 | No clear effect |
| add AAM-softmax identity enhancement instead of plain softmax (ablation) | FaceTracer · HiRes swapped faces (S1) | Top-1 accuracy (%): 89.51 -> 98.80 | Improved |
| add AAM-softmax identity enhancement instead of plain softmax (ablation) | FaceTracer · InfoSwap swapped faces (S1) | Top-1 accuracy (%): 96.64 -> 97.97 | Improved |
| add reference images in training for cross-method transfer (S1/S2 vs S3) | FaceTracer trained on HiRes · InfoSwap test images | Top-1 accuracy (%): 87.84 -> 98.06 | Improved |
| train on mixture of four swap methods instead of one | FaceTracer · HiRes swapped faces (S1) | Top-1 accuracy (%): 98.80 -> 99.23 | No clear effect |
| swap faces twice with two targets (continuous swapping) | FaceTracer · HiRes swapped faces (S3) | Top-1 accuracy (%): 93.34 -> 84.73 | Hurt |
Closest papers by meaning
- Robust Secure Swap: Responsible Face Swap With Persons of Interest Redaction and Provenance Traceability (ICML 2025 · similarity 0.89)
- Forensics Adapter: Adapting CLIP for Generalizable Face Forgery Detection (CVPR 2025 · similarity 0.86)
- Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection (ICLR 2024 · similarity 0.85)
- Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes (NeurIPS 2025 · similarity 0.84)
- Identity-Aware Vision-Language Model for Explainable Face Forgery Detection (AAAI 2026 · 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.
