Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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.

Tianyun Yang, Ziyao Huang, Juan Cao, Lei Li, Xirong Li• 2022

Related benchmarks

TaskDatasetResultRank
Deepfake AttributionDF40 and FFHQ unseen generators
SimSwap Accuracy61.6
54
AttributionWildDeepfake
Accuracy4.24
34
Deepfake AttributionDiffusionAct unseen
Accuracy75.36
20
Deepfake AttributionFLOAT unseen
Accuracy74.56
20
Deepfake AttributionReal3DPortrait unseen
Accuracy71.44
20
Deepfake AttributionCeleb-DF
Accuracy41.36
20
Deepfake AttributionDFDC
Accuracy48.08
20
Deepfake AttributionFLUX unseen
Accuracy17.76
20
Deepfake AttributionUnseen Generators Average
Accuracy27.16
20
Deepfake AttributionLivePortrait unseen
Accuracy4.24
20
Showing 10 of 31 rows

Other info

Follow for update