Self-Supervised Learning for Detecting AI-Generated Faces as Anomalies
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908176119496704 |
|---|---|
| author | Zou, Mian Yu, Baosheng Zhan, Yibing Ma, Kede |
| author_facet | Zou, Mian Yu, Baosheng Zhan, Yibing Ma, Kede |
| contents | 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}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_02207 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-Supervised Learning for Detecting AI-Generated Faces as Anomalies Zou, Mian Yu, Baosheng Zhan, Yibing Ma, Kede Computer Vision and Pattern Recognition 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}. |
| title | Self-Supervised Learning for Detecting AI-Generated Faces as Anomalies |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.02207 |