๐Ÿ“–
CLIP-Flow: A Universal Discriminator for AI-Generated Images Inspired by Anomaly Detection
Zhipeng Yuan, Kai Wang, Weize Quan, Dong-Ming Yan, Tieru Wu

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

Science & Mathematics Published 2025 Verification Pending

Overview & Synopsis

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.

Indexed from repository: HAL Open Science (hal.science)
Loading document from verified source...
Keyboard Shortcuts: ← / → for pages • + / - for zoom • 0 to fit width Powered by Mozilla PDF.js v3.11

Document Information

Document Title CLIP-Flow: A Universal Discriminator for AI-Generated Images Inspired by Anomaly Detection
Author / Organization Zhipeng Yuan, Kai Wang, Weize Quan, Dong-Ming Yan, Tieru Wu
Subject & Discipline Multidisciplinary Academic Open Research
Categories Science & Mathematics
Publication Year 2025
License / Rights Open Access / Creative Commons
Resource Verification Listed PDF (Verification Pending)
Original Host Website HAL Open Science (hal.science)
File Format application/pdf (Portable Document Format)
Language EN
Catalog ID DOC-216018
Original Source Link Visit Source Page on hal.science »