Data-Agnostic Face Image Synthesis Detection Using Bayesian CNNs
This addresses the societal issue of synthetic face image misuse by providing a more practical detection solution, though it is incremental as it builds on existing anomaly detection frameworks.
The paper tackles the problem of detecting synthetic face images by proposing a data-agnostic anomaly detection method that uses only real data for training, achieving competitive performance against state-of-the-art methods that require synthetic data.
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.