# Data-Agnostic Face Image Synthesis Detection Using Bayesian CNNs

arXiv: https://arxiv.org/abs/2401.04241 · HTML: https://mlsanity.com/paper/2401.04241/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 37 references that are in the map.
- First posted on arXiv 8 Jan 2024.

## Builds on (most cited first, 26 of 26)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [NVAE: A Deep Hierarchical Variational Autoencoder](https://mlsanity.com/paper/2007.03898/) (2020)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)
- [StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets](https://mlsanity.com/paper/2202.00273/) (2022)
- [MesoNet: a Compact Facial Video Forgery Detection Network](https://mlsanity.com/paper/1809.00888/) (2018)
- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [Detecting and Simulating Artifacts in GAN Fake Images](https://mlsanity.com/paper/1907.06515/) (2019)
- [DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection](https://mlsanity.com/paper/2001.00179/) (2020)
- [Are GAN generated images easy to detect? A critical analysis of the state-of-the-art](https://mlsanity.com/paper/2104.02617/) (2021)
- [Detecting GAN generated Fake Images using Co-occurrence Matrices](https://mlsanity.com/paper/1903.06836/) (2019)
- [Data-Efficient Instance Generation from Instance Discrimination](https://mlsanity.com/paper/2106.04566/) (2021)
- [Bayesian Model Selection, the Marginal Likelihood, and Generalization](https://mlsanity.com/paper/2202.11678/) (2022)
- [SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes](https://mlsanity.com/paper/2211.11296/) (2022)
- [Learning to Detect Fake Face Images in the Wild](https://mlsanity.com/paper/1809.08754/) (2018)
- [DeepFakes Evolution: Analysis of Facial Regions and Fake Detection Performance](https://mlsanity.com/paper/2004.07532/) (2020)
- [DepthFake: a depth-based strategy for detecting Deepfake videos](https://mlsanity.com/paper/2208.11074/) (2022)

## Built on by (most cited first, 2 of 2)

- [DiffFake: Exposing Deepfakes using Differential Anomaly Detection](https://mlsanity.com/paper/2502.16247/) (2025)
- [μFlow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors](https://mlsanity.com/paper/2606.30528/) (2026)

## Abstract (arXiv)

Face image synthesis detection is considerably gaining attention because of the potential negative impact on society that this type of synthetic data brings. In this paper, we propose a data-agnostic solution to detect the face image synthesis process. Specifically, our solution is based on an anomaly detection framework that requires only real data to learn the inference process. It is therefore data-agnostic in the sense that it requires no synthetic face images. The solution uses the posterior probability with respect to the reference data to determine if new samples are synthetic or not. Our evaluation results using different synthesizers show that our solution is very competitive against the state-of-the-art, which requires synthetic data for training.