đ€ AI Summary
To address deepfake detection under constrained computational resources and scarce training dataâparticularly when confronting novel forgery techniquesâthis paper first uncovers the structured semantic sensitivity of StyleGANâs latent space to forgery discrimination. We propose a lightweight binary classification paradigm that leverages latent-space features for unsupervised or few-shot discriminative learning, thereby constructing high-dimensional facial semantic representations. Our approach significantly enhances cold-start adaptability and cross-forensic-type generalization. On standard benchmarks, it surpasses state-of-the-art methods, achieving substantial accuracy gainsâespecially in low-data regimesâwhile reducing model parameter count by over 90%.
đ Abstract
The classification of forged videos has been a challenge for the past few years. Deepfake classifiers can now reliably predict whether or not video frames have been tampered with. However, their performance is tied to both the dataset used for training and the analyst's computational power. We propose a deepfake detection method that operates in the latent space of a state-of-the-art generative adversarial network (GAN) trained on high-quality face images. The proposed method leverages the structure of the latent space of StyleGAN to learn a lightweight binary classification model. Experimental results on standard datasets reveal that the proposed approach outperforms other state-of-the-art deepfake classification methods, especially in contexts where the data available to train the models is rare, such as when a new manipulation method is introduced. To the best of our knowledge, this is the first study showing the interest of the latent space of StyleGAN for deepfake classification. Combined with other recent studies on the interpretation and manipulation of this latent space, we believe that the proposed approach can further help in developing frugal deepfake classification methods based on interpretable high-level properties of face images.