Deepfake Network Architecture Attribution
About
With the rapid progress of generation technology, it has become necessary to attribute the origin of fake images. Existing works on fake image attribution perform multi-class classification on several Generative Adversarial Network (GAN) models and obtain high accuracies. While encouraging, these works are restricted to model-level attribution, only capable of handling images generated by seen models with a specific seed, loss and dataset, which is limited in real-world scenarios when fake images may be generated by privately trained models. This motivates us to ask whether it is possible to attribute fake images to the source models' architectures even if they are finetuned or retrained under different configurations. In this work, we present the first study on Deepfake Network Architecture Attribution to attribute fake images on architecture-level. Based on an observation that GAN architecture is likely to leave globally consistent fingerprints while traces left by model weights vary in different regions, we provide a simple yet effective solution named DNA-Det for this problem. Extensive experiments on multiple cross-test setups and a large-scale dataset demonstrate the effectiveness of DNA-Det.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Deep Face Attribution | OW-DFA (All) | Accuracy54.4 | 18 | |
| Deep Face Attribution | OW-DFA (Novel) | Accuracy34.8 | 18 | |
| Deep Face Attribution | OW-DFA Known | ACC0.891 | 18 | |
| Deepfake Attribution | Unseen Advanced Generators VAE, HART, FLUX | VAE Accuracy80.16 | 14 | |
| Detection | Unseen Datasets Average | Accuracy75 | 14 | |
| Deepfake Detection | Unseen Advanced Generators VAE, HART, FLUX | Average Accuracy44.82 | 14 | |
| Deepfake Detection | DF40 and FFHQ unseen generators | Average Accuracy (ACC)86.99 | 14 | |
| Attribution | DFDC | Accuracy47.6 | 14 | |
| Deepfake Attribution | DF40 and FFHQ unseen generators | FFHQ Accuracy8.16 | 14 | |
| Attribution | Celeb-DF | Accuracy18.72 | 14 |