Self-Supervised Learning for Detecting AI-Generated Faces as Anomalies
This addresses the challenge of adapting detectors to rapidly evolving AI face generators for security and verification applications, representing a novel method for a known bottleneck.
The paper tackles the problem of detecting AI-generated faces by proposing a self-supervised anomaly detection method that learns camera-intrinsic and face-specific features from photographic images, achieving validated effectiveness in experiments.
The detection of AI-generated faces is commonly approached as a binary classification task. Nevertheless, the resulting detectors frequently struggle to adapt to novel AI face generators, which evolve rapidly. In this paper, we describe an anomaly detection method for AI-generated faces by leveraging self-supervised learning of camera-intrinsic and face-specific features purely from photographic face images. The success of our method lies in designing a pretext task that trains a feature extractor to rank four ordinal exchangeable image file format (EXIF) tags and classify artificially manipulated face images. Subsequently, we model the learned feature distribution of photographic face images using a Gaussian mixture model. Faces with low likelihoods are flagged as AI-generated. Both quantitative and qualitative experiments validate the effectiveness of our method. Our code is available at \url{https://github.com/MZMMSEC/AIGFD_EXIF.git}.