# Face-Trace: Open-Set Attribution and Progressive Discovery of Synthetic Face Generators

arXiv: https://arxiv.org/abs/2607.07545 · HTML: https://mlsanity.com/paper/2607.07545/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 47 references that are in the map.
- First posted on arXiv 8 Jul 2026.

## Builds on (most cited first, 30 of 33)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [On the Importance of Gradients for Detecting Distributional Shifts in the Wild](https://mlsanity.com/paper/2110.00218/) (2021)
- [Learning to Discover Novel Visual Categories via Deep Transfer Clustering](https://mlsanity.com/paper/1908.09884/) (2019)
- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models](https://mlsanity.com/paper/2210.06998/) (2022)
- [A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges](https://mlsanity.com/paper/2110.14051/) (2021)
- [Parametric Classification for Generalized Category Discovery: A Baseline Study](https://mlsanity.com/paper/2211.11727/) (2022)
- [Towards Discovery and Attribution of Open-world GAN Generated Images](https://mlsanity.com/paper/2105.04580/) (2021)
- [Generalizable Synthetic Image Detection via Language-guided Contrastive Learning](https://mlsanity.com/paper/2305.13800/) (2023)
- [Deepfake Network Architecture Attribution](https://mlsanity.com/paper/2202.13843/) (2022)
- [RepMix: Representation Mixing for Robust Attribution of Synthesized Images](https://mlsanity.com/paper/2207.02063/) (2022)
- [Progressive Open Space Expansion for Open-Set Model Attribution](https://mlsanity.com/paper/2303.06877/) (2023)
- [AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmark](https://mlsanity.com/paper/2406.00783/) (2024)
- [Novel Class Discovery: an Introduction and Key Concepts](https://mlsanity.com/paper/2302.12028/) (2023)
- [ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery](https://mlsanity.com/paper/2504.03755/) (2025)
- [Are CLIP features all you need for Universal Synthetic Image Origin Attribution?](https://mlsanity.com/paper/2408.09153/) (2024)
- [Forensic Self-Descriptions Are All You Need for Zero-Shot Detection, Open-Set Source Attribution, and Clustering of AI-generated Images](https://mlsanity.com/paper/2503.21003/) (2025)
- [WILD: a new in-the-Wild Image Linkage Dataset for synthetic image attribution](https://mlsanity.com/paper/2504.19595/) (2025)
- [Deepfake Media Forensics: State of the Art and Challenges Ahead](https://mlsanity.com/paper/2408.00388/) (2024)
- [BOSC: A Backdoor-based Framework for Open Set Synthetic Image Attribution](https://mlsanity.com/paper/2405.11491/) (2024)
- [Is it all a cluster game? -- Exploring Out-of-Distribution Detection based on Clustering in the Embedding Space](https://mlsanity.com/paper/2203.08549/) (2022)
- [Open-World Deepfake Attribution via Confidence-Aware Asymmetric Learning](https://mlsanity.com/paper/2512.12667/) (2025)
- [Face Deepfakes -- A Comprehensive Review](https://mlsanity.com/paper/2502.09812/) (2025)

## Abstract (arXiv)

Recent advances in generative Artificial Intelligence have made synthetic face images increasingly realistic, creating new challenges for multimedia forensics. Source attribution methods should identify the generator of an image when the source is known, but also handle samples produced by unseen models. Most existing approaches, however, address synthetic face attribution in a closed-set setting, assuming that test samples can only originate from generators observed during training. This assumption does not hold in real-world scenarios, where new generators continuously appear and detecting an image as unknown is not sufficient, since rejected samples should also be organized according to their underlying sources. We introduce Face-Trace, a pipeline for open-set synthetic face source attribution that combines known generator classification, energy-based rejection, and unknown generator discovery. A classifier trained on frozen I-JEPA embeddings attributes known generators, while rejected samples are represented by combining projected I-JEPA features with complementary forensic traces and grouped to identify coherent sets of samples produced by unknown generators. We also extend the discovery stage to an incremental scenario, where rejected samples arrive over time. Experiments on the WILD dataset show 96.73% closed-set attribution accuracy, while rejection reaches 71.25% balanced accuracy and rejected samples are clustered into meaningful unknown-generator groups, with an Adjusted Rand Index of 0.81, a Normalized Mutual Information of 0.90, and an overall purity of 87.74%. In the incremental setting, the discovered generator space is progressively extended while maintaining a final purity of 99.23%, and cross-dataset experiments suggest that the pipeline can operate beyond the original data distribution.