$μ$Flow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors
For deepfake detection, this work provides a novel one-class approach that generalizes to unseen generators without requiring fake training data, addressing a key limitation of current supervised methods.
μFlow is a one-class deepfake detector trained only on real images that leverages averaging to amplify generative traces, achieving state-of-the-art out-of-distribution generalization and significantly outperforming existing detectors.
Current generative models, including GANs and diffusion models, have reached an outstanding level of photorealism, posing significant risks to privacy and security. To ensure real-world applicability, deepfake detectors must generalise effectively to unseen generators. However, most existing approaches rely on supervised training with both real and fake images, which limits their generalisation especially across generators categories (e.g. GANs vs DMs). In this work, we introduce $μ$Flow, a one-class deepfake detector trained only on real images without relying on pseudo-deepfakes or synthetic artifacts. Our approach builds on the observation that averaging multiple images amplifies consistent generative traces, producing highly discriminative feature representations. We leverage this property by modelling the distribution of features extracted from averaged images and training a normalizing flow to align the feature space of individual images with this distribution. This alignment yields a likelihood-based criterion that separates real and fake samples while promoting strong generalisation. We evaluate $μ$Flow on a fully out-of-distribution setting, where both real and fake datasets are unseen during training. Experimental results show that our method significantly outperforms SOTA detectors. Project page: https://opontorno.github.io/MuFlow.