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

• URL: http://arxiv.org/abs/2508.09477v1
• Date: Wed, 13 Aug 2025 04:12:37 GMT
• Title: CLIP-Flow: A Universal Discriminator for AI-Generated Images Inspired by Anomaly Detection
• Abstract summary: We propose a universal AI-generated image detector from the perspective of anomaly detection.<n>Our discriminator does not need to access any AIIs and learn a generalizable representation with unsupervised learning.
• Score: 15.404234946542692
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Generated Images Are Easier to Forget: A Machine Unlearning Perspective for Synthetic Image Detection [107.62647907393377]
  Large-scale vision models (LVMs) pre-trained on web-scale datasets exhibit exceptional generalization power.<n>We introduce two detection methods: 1) data-free detection, which prunes model parameters to induce unlearning without data access, and 2) data-driven detection, which optimize LVMs to unlearn knowledge tied to generated images.
  arXiv  Detail & Related papers  (2026-08-01T15:33:15Z)
• RAID: Towards Robust AI-Generated Image Detection with Bit-Reversed Images [25.492080916045012]
  We investigate AI-generated image detection using bit-planes, and introduce the bit-reversed image.<n>We propose a simple yet effective pipeline consisting of construction of bit-reversed images, gradient-based patch selection and a convolutional classifier.<n>Our approach outperforms existing methods on over 40 benchmarks, and is nearly 100 times faster than counterparts.
  arXiv  Detail & Related papers  (2026-07-31T02:53:07Z)
• TAP into the Patch Tokens: Leveraging Vision Foundation Model Features for AI-Generated Image Detection [0.10705399532413612]
  We present a comprehensive benchmark across multiple vision foundation models (VFMs)<n>We evaluate their out-of-the-box performance for detecting fully-generated AI-images and AI-inpainted images.<n>We propose a simple redesign of the classifier head by utilizing tunable attention pooling (TAP), which aggregates output tokens into a refined global representation.
  arXiv  Detail & Related papers  (2026-04-29T15:03:25Z)
• Attribution as Retrieval: Model-Agnostic AI-Generated Image Attribution [24.28021197076691]
  This work presents a new paradigm for AI-generated image attribution by formulating it as an instance retrieval problem.<n>We propose an efficient model-agnostic framework, called Low-bIt-plane-based Deepfake Attribution (LIDA)<n>Experiments demonstrate that LIDA achieves state-of-the-art performance for both Deepfake detection and image attribution under zero- and few-shot settings.
  arXiv  Detail & Related papers  (2026-03-11T09:40:00Z)
• Detecting AI-Generated Images via Distributional Deviations from Real Images [6.615773227400183]
  We propose a Masking-based Pre-trained model Fine-Tuning (MPFT) strategy, which introduces a Texture-Aware Masking (TAM) mechanism to mask textured areas containing generative model-specific patterns during fine-tuning.<n>Our method, fine-tuned with only a minimal number of images, significantly outperforms existing approaches, achieving up to 98.2% and 94.6% average accuracy on the two datasets, respectively.
  arXiv  Detail & Related papers  (2026-01-07T05:00:13Z)
• Self-Supervised AI-Generated Image Detection: A Camera Metadata Perspective [80.10217707456046]
  We introduce a self-supervised approach for detecting AI-generated images that leverages camera metadata.<n>We train a feature extractor solely on camera-captured photographs by classifying categorical EXIF tags.<n>Our detectors deliver strong generalization to in-the-wild samples and robustness to common benign image perturbations.
  arXiv  Detail & Related papers  (2025-12-05T11:53:18Z)
• Towards Generalizable AI-Generated Image Detection via Image-Adaptive Prompt Learning [30.415427474641813]
  We propose a novel framework named Image-Adaptive Prompt Learning (IAPL), which enhances flexibility in processing diverse testing images.<n>It consists of two adaptive modules, i.e., the Conditional Information Learner and the Confidence-Driven Adaptive Prediction.<n>Experiments show that IAPL achieves state-of-the-art performance, with 95.61% and 96.7% mean accuracy on two widely used UniversalFakeDetect and GenImage datasets.
  arXiv  Detail & Related papers  (2025-08-03T05:41:24Z)
• Bi-Level Optimization for Self-Supervised AI-Generated Face Detection [56.57881725223548]
  We introduce a self-supervised method for AI-generated face detectors based on bi-level optimization.<n>Our detectors significantly outperform existing approaches in both one-class and binary classification settings.
  arXiv  Detail & Related papers  (2025-07-30T16:38:29Z)
• Quality Assessment and Distortion-aware Saliency Prediction for AI-Generated Omnidirectional Images [70.49595920462579]
  This work studies the quality assessment and distortion-aware saliency prediction problems for AIGODIs.<n>We propose two models with shared encoders based on the BLIP-2 model to evaluate the human visual experience and predict distortion-aware saliency for AI-generated omnidirectional images.
  arXiv  Detail & Related papers  (2025-06-27T05:36:04Z)
• Few-Shot Learner Generalizes Across AI-Generated Image Detection [14.069833211684715]
  Few-Shot Detector (FSD) is a novel AI-generated image detector which learns a specialized metric space for effectively distinguishing unseen fake images.<n>Experiments show FSD achieves state-of-the-art performance by $+11.6%$ average accuracy on the GenImage dataset with only $10$ additional samples.
  arXiv  Detail & Related papers  (2025-01-15T12:33:11Z)
• Self-Supervised Learning for Detecting AI-Generated Faces as Anomalies [58.11545090128854]
  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.<n>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.
  arXiv  Detail & Related papers  (2025-01-04T06:23:24Z)
• Detecting Discrepancies Between AI-Generated and Natural Images Using Uncertainty [91.64626435585643]
  We propose a novel approach for detecting AI-generated images by leveraging predictive uncertainty to mitigate misuse and associated risks.<n>The motivation arises from the fundamental assumption regarding the distributional discrepancy between natural and AI-generated images.<n>We propose to leverage large-scale pre-trained models to calculate the uncertainty as the score for detecting AI-generated images.
  arXiv  Detail & Related papers  (2024-12-08T11:32:25Z)
• Zero-Shot Detection of AI-Generated Images [54.01282123570917]
  We propose a zero-shot entropy-based detector (ZED) to detect AI-generated images. Inspired by recent works on machine-generated text detection, our idea is to measure how surprising the image under analysis is compared to a model of real images. ZED achieves an average improvement of more than 3% over the SoTA in terms of accuracy.
  arXiv  Detail & Related papers  (2024-09-24T08:46:13Z)
• RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detection [60.960988614701414]
  RIGID is a training-free and model-agnostic method for robust AI-generated image detection. RIGID significantly outperforms existing trainingbased and training-free detectors.
  arXiv  Detail & Related papers  (2024-05-30T14:49:54Z)
• Online Detection of AI-Generated Images [17.30253784649635]
  We study generalization in this setting, training on N models and testing on the next (N+k) We extend this approach to pixel prediction, demonstrating strong performance using automatically-generated inpainted data. In addition, for settings where commercial models are not publicly available for automatic data generation, we evaluate if pixel detectors can be trained solely on whole synthetic images.
  arXiv  Detail & Related papers  (2023-10-23T17:53:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.