Communication Dans Un Congrès Année : 2025

CLIP-Flow: A Universal Discriminator for AI-Generated Images Inspired by Anomaly Detection

Résumé

With the rapid advancement of AI generative models, the visual quality of AI-generated images (AIIs) has become increasingly close to natural images, which inevitably raises security concerns. Most AII detectors often employ the conventional image classification pipeline with natural images and AIIs (generated by a generative model), which can result in limited detection performance for AIIs from unseen generative models. To solve this, we proposed a universal AI-generated image detector from the perspective of anomaly detection. Our discriminator does not need to access any AIIs and learn a generalizable representation with unsupervised learning. Specifically, we use the pre-trained CLIP encoder as the feature extractor and design a normalizing flow-like unsupervised model. Instead of AIIs, proxy images, e.g., obtained by applying a spectral modification operation on natural images, are used for training. Our models are trained by minimizing the likelihood of proxy images, optionally combined with maximizing the likelihood of natural images. Extensive experiments demonstrate the effectiveness of our method on AIIs produced by various image generators.

Fichier principal
Vignette du fichier
DFF_2025_Preprint.pdf (1.35 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05296631 , version 1 (07-10-2025)

Licence

Identifiants

Citer

Zhipeng Yuan, Kai Wang, Weize Quan, Dong-Ming Yan, Tieru Wu. CLIP-Flow: A Universal Discriminator for AI-Generated Images Inspired by Anomaly Detection. DFF 2025 - 1st Deepfake Forensics Workshop: Detection, Attribution, Recognition, and Adversarial Challenges in the Era of AI-Generated Media (DFF 2025), Oct 2025, Dublin, Ireland. pp.1-9, ⟨10.1145/3746265.3759663⟩. ⟨hal-05296631⟩
159 Consultations
354 Téléchargements

Altmetric

Partager

  • More