CINEMAE: Leveraging Frozen Masked Autoencoders for Cross-Generator AI Image Detection

• URL: http://arxiv.org/abs/2511.06325v1
• Date: Sun, 09 Nov 2025 11:05:45 GMT
• Title: CINEMAE: Leveraging Frozen Masked Autoencoders for Cross-Generator AI Image Detection
• Authors: Minsuk Jang, Hyeonseo Jeong, Minseok Son, Changick Kim,
• Abstract summary: CINEMAE adapts the core principles of text detection methods to the visual domain.<n>We trained exclusively on Stable Diffusion v1.4, our method achieves over 95% accuracy on all eight unseen generators in the GenImage benchmark.<n>This demonstrates that context-conditional reconstruction uncertainty provides a robust, transferable signal for AIGC detection.
• Score: 25.84217122259626
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: While context-based detectors have achieved strong generalization for AI-generated text by measuring distributional inconsistencies, image-based detectors still struggle with overfitting to generator-specific artifacts. We introduce CINEMAE, a novel paradigm for AIGC image detection that adapts the core principles of text detection methods to the visual domain. Our key insight is that Masked AutoEncoder (MAE), trained to reconstruct masked patches conditioned on visible context, naturally encodes semantic consistency expectations. We formalize this reconstruction process probabilistically, computing conditional Negative Log-Likelihood (NLL, p(masked | visible)) to quantify local semantic anomalies. By aggregating these patch-level statistics with global MAE features through learned fusion, CINEMAE achieves strong cross-generator generalization. Trained exclusively on Stable Diffusion v1.4, our method achieves over 95% accuracy on all eight unseen generators in the GenImage benchmark, substantially outperforming state-of-the-art detectors. This demonstrates that context-conditional reconstruction uncertainty provides a robust, transferable signal for AIGC detection.

Related papers

• 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)
• Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection [30.53429368921365]
  A critical limitation of current detectors is their failure to generalize to images from unseen generative models.<n>We introduce a simple yet remarkably effective pixel-level mapping pre-processing step to disrupt the pixel value distribution of images.<n>We show that our approach significantly boosts the cross-generator performance of state-of-the-art detectors.
  arXiv  Detail & Related papers  (2025-12-19T08:47:09Z)
• Towards Sustainable Universal Deepfake Detection with Frequency-Domain Masking [17.153540024060483]
  Universal deepfake detection aims to identify AI-generated images across a broad range of generative models, including unseen ones.<n>This requires robust generalization to new and unseen deepfakes, which emerge frequently.<n>In this work, we explore frequency-domain masking as a training strategy for deepfake detectors.
  arXiv  Detail & Related papers  (2025-12-08T21:08:25Z)
• Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images [96.43608872116347]
  AnomReason is a large-scale benchmark with structured annotations as quadruple textbfAnomAgent<n>AnomReason and AnomAgent serve as a foundation for measuring and improving the semantic plausibility of AI-generated images.
  arXiv  Detail & Related papers  (2025-10-11T14:09:24Z)
• Quality-Aware Language-Conditioned Local Auto-Regressive Anomaly Synthesis and Detection [30.77558600436759]
  ARAS is a language-conditioned, auto-regressive anomaly synthesis approach.<n>It injects local, text-specified defects into normal images via token-anchored latent editing.<n>It significantly enhances defect realism, preserves fine-grained material textures, and provides continuous semantic control over synthesized anomalies.
  arXiv  Detail & Related papers  (2025-08-05T15:07:32Z)
• 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)
• RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectors [57.81012948133832]
  We present RAID (Robust evaluation of AI-generated image Detectors), a dataset of 72k diverse and highly transferable adversarial examples.<n>Our methodology generates adversarial images that transfer with a high success rate to unseen detectors.<n>Our findings indicate that current state-of-the-art AI-generated image detectors can be easily deceived by adversarial examples.
  arXiv  Detail & Related papers  (2025-06-04T14:16:00Z)
• Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image Detection [11.907536189598577]
  Current AIGC detectors often achieve near-perfect accuracy on images produced by the same generator used for training but struggle to generalize to outputs from unseen generators.<n>We trace this failure in part to latent prior bias: detectors learn shortcuts tied to patterns stemming from the initial noise vector rather than learning robust generative artifacts.<n>We propose On-Manifold Adversarial Training (OMAT), which generates adversarial examples that remain on the generator's output manifold.
  arXiv  Detail & Related papers  (2025-06-01T07:20:45Z)
• Zooming In on Fakes: A Novel Dataset for Localized AI-Generated Image Detection with Forgery Amplification Approach [69.01456182499486]
  textbfBR-Gen is a large-scale dataset of 150,000 locally forged images with diverse scene-aware annotations.<n>textbfNFA-ViT is a Noise-guided Forgery Amplification Vision Transformer that enhances the detection of localized forgeries.
  arXiv  Detail & Related papers  (2025-04-16T09:57:23Z)
• Towards Generalizable Forgery Detection and Reasoning [23.858913560970866]
  We formulate detection and explanation as a unified Forgery Detection and Reasoning task (FDR-Task)<n>We introduce the Multi-Modal Forgery Reasoning dataset (MMFR-Dataset), a large-scale dataset containing 120K images across 10 generative models, with 378K reasoning annotations on forgery attributes.<n>Experiments across multiple generative models demonstrate that FakeReasoning achieves robust generalization and outperforms state-of-the-art methods on both detection and reasoning tasks.
  arXiv  Detail & Related papers  (2025-03-27T06:54:06Z)
• LADMIM: Logical Anomaly Detection with Masked Image Modeling in Discrete Latent Space [0.0]
  Masked image modeling is a self-supervised learning technique that predicts the feature representation of masked regions in an image. We propose a novel approach that leverages the characteristics of MIM to detect logical anomalies effectively. We evaluate the proposed method on the MVTecLOCO dataset, achieving an average AUC of 0.867.
  arXiv  Detail & Related papers  (2024-10-14T07:50:56Z)
• DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [55.48770333927732]
  We propose a Difusion-based Anomaly Detection (DiAD) framework for multi-class anomaly detection. It consists of a pixel-space autoencoder, a latent-space Semantic-Guided (SG) network with a connection to the stable diffusion's denoising network, and a feature-space pre-trained feature extractor. Experiments on MVTec-AD and VisA datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-12-11T18:38:28Z)
• Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting [133.55037976429088]
  We investigate the adversarial robustness of vision transformers equipped with BERT pretraining (e.g., BEiT, MAE) A surprising observation is that MAE has significantly worse adversarial robustness than other BERT pretraining methods. We propose a simple yet effective way to boost the adversarial robustness of MAE.
  arXiv  Detail & Related papers  (2023-08-20T16:27:17Z)

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.