# Only Train Once: Uncertainty-Aware One-Class Learning for Face Authenticity Detection

arXiv: https://arxiv.org/abs/2605.10040 · HTML: https://mlsanity.com/paper/2605.10040/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 11 May 2026.

## Builds on (most cited first, 23 of 23)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Improving Variational Inference with Inverse Autoregressive Flow](https://mlsanity.com/paper/1606.04934/) (2016)
- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)
- [Face X-ray for More General Face Forgery Detection](https://mlsanity.com/paper/1912.13458/) (2019)
- [DIRE for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2303.09295/) (2023)
- [DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection](https://mlsanity.com/paper/2001.00179/) (2020)
- [Talking Face Generation by Adversarially Disentangled Audio-Visual Representation](https://mlsanity.com/paper/1807.07860/) (2018)
- [Media Forensics and DeepFakes: an overview](https://mlsanity.com/paper/2001.06564/) (2020)
- [DF40: Toward Next-Generation Deepfake Detection](https://mlsanity.com/paper/2406.13495/) (2024)
- [Deepfake Generation and Detection: A Benchmark and Survey](https://mlsanity.com/paper/2403.17881/) (2024)
- [Face Forgery Detection by 3D Decomposition](https://mlsanity.com/paper/2011.09737/) (2020)
- [DPE: Disentanglement of Pose and Expression for General Video Portrait Editing](https://mlsanity.com/paper/2301.06281/) (2023)
- [Region-Aware Face Swapping](https://mlsanity.com/paper/2203.04564/) (2022)
- [MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection](https://mlsanity.com/paper/2404.08452/) (2024)
- [Deepfakes, Misinformation, and Disinformation in the Era of Frontier AI, Generative AI, and Large AI Models](https://mlsanity.com/paper/2311.17394/) (2023)
- [A Study of the Human Perception of Synthetic Faces](https://mlsanity.com/paper/2111.04230/) (2021)
- [DIP: Diffusion Learning of Inconsistency Pattern for General DeepFake Detection](https://mlsanity.com/paper/2410.23663/) (2024)
- [Model Discrepancy Learning: Synthetic Faces Detection Based on Multi-Reconstruction](https://mlsanity.com/paper/2504.07382/) (2025)
- [Generalizable and Adaptive Continual Learning Framework for AI-generated Image Detection](https://mlsanity.com/paper/2601.05580/) (2026)

## Abstract (arXiv)

The rapid evolution of generative paradigms has enabled the creation of highly realistic imagery, which escalating the risks of identity fraud and the dissemination of disinformation. Most existing approaches frame face forgery detection as a fully supervised binary classification problem. Consequently, these models typically exhibit significant performance decay when tasked with detecting forgeries from previously unseen generative paradigms. Furthermore, these methods focus exclusively on either DeepFakes or fully synthesized faces, thereby failing to provide a generalized framework for universal face forgery detection. In this paper, we address this challenge by introducing FADNet (Face Authenticity Detector Net), % a self-supervised framework that which reformulates face forgery detection as a one-class classification (OCC) task. By training exclusively on authentic facial data to capture their intrinsic representations, FADNet flags any image whose feature embedding deviates significantly from the learned distribution of real faces as a forgery. The framework incorporates Evidential Deep Learning (EDL) to quantify predictive uncertainty and utilizes a plug-and-play pseudo-forgery image generator (PFIG) to tighten decision boundaries around authentic data. Extensive experimental evaluations on the DF40 and ASFD benchmarks demonstrate that FADNet achieves superior performance and generalization capabilities. Specifically, FADNet substantially outperforms existing state-of-the-art (SOTA) methods, yielding a remarkable average accuracy of 96.63% and an average precision of 98.83%.