Epistemic Uncertainty for Generated Image Detection

• URL: http://arxiv.org/abs/2412.05897v2
• Date: Mon, 03 Nov 2025 07:06:56 GMT
• Title: Epistemic Uncertainty for Generated Image Detection
• Authors: Jun Nie, Yonggang Zhang, Tongliang Liu, Yiu-ming Cheung, Bo Han, Xinmei Tian,
• Abstract summary: We introduce a novel framework for AI-generated image detection through epistemic uncertainty, aiming to address critical security concerns in the era of generative models.<n>Our key insight stems from the observation that distributional discrepancies between training and testing data manifest distinctively in the epistemic uncertainty space of machine learning models.
• Score: 107.62647907393377
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce a novel framework for AI-generated image detection through epistemic uncertainty, aiming to address critical security concerns in the era of generative models. Our key insight stems from the observation that distributional discrepancies between training and testing data manifest distinctively in the epistemic uncertainty space of machine learning models. In this context, the distribution shift between natural and generated images leads to elevated epistemic uncertainty in models trained on natural images when evaluating generated ones. Hence, we exploit this phenomenon by using epistemic uncertainty as a proxy for detecting generated images. This converts the challenge of generated image detection into the problem of uncertainty estimation, underscoring the generalization performance of the model used for uncertainty estimation. Fortunately, advanced large-scale vision models pre-trained on extensive natural images have shown excellent generalization performance for various scenarios. Thus, we utilize these pre-trained models to estimate the epistemic uncertainty of images and flag those with high uncertainty as generated. Extensive experiments demonstrate the efficacy of our method. Code is available at https://github.com/tmlr-group/WePe.

Related papers

• Diffusion Epistemic Uncertainty with Asymmetric Learning for Diffusion-Generated Image Detection [10.061197311881287]
  We propose a novel framework, Diffusion Epistemic Uncertainty with Asymmetric Learning(DEUA), for detecting generated images.<n>We introduce Diffusion Epistemic Uncertainty(DEU) estimation via the Laplace approximation to assess the proximity of data to the manifold of diffusion-generated samples.
  arXiv  Detail & Related papers  (2026-01-21T03:57:15Z)
• Detecting Generated Images by Fitting Natural Image Distributions [75.31113784234877]
  We propose a novel framework that exploits geometric differences between the data manifold of natural and generated images.<n>We employ a pair of functions engineered to yield consistent outputs for natural images but divergent outputs for generated ones.<n>An image is identified as generated if a transformation along its data manifold induces a significant change in the loss value of a self-supervised model pre-trained on natural images.
  arXiv  Detail & Related papers  (2025-11-03T07:20:38Z)
• 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)
• Are vision language models robust to uncertain inputs? [5.249651874118556]
  We show that newer and larger vision language models exhibit improved robustness compared to earlier models, but still suffer from a tendency to strictly follow instructions.<n>For natural images such as ImageNet, this limitation can be overcome without pipeline modifications.<n>We propose a novel mechanism based on caption diversity to reveal a model's internal uncertainty.
  arXiv  Detail & Related papers  (2025-05-17T03:16:49Z)
• Bayesian generative models can flag performance loss, bias, and out-of-distribution image content [15.835055687646507]
  Generative models are popular for medical imaging tasks such as anomaly detection, feature extraction, data visualization, or image generation.<n>Since they are parameterized by deep learning models, they are often sensitive to distribution shifts and unreliable when applied to out-of-distribution data.<n>We show how pixel-wise uncertainty can detect out-of-distribution image content such as ink, rulers, and patches.
  arXiv  Detail & Related papers  (2025-03-21T18:45:28Z)
• 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. 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)
• Understanding and Improving Training-Free AI-Generated Image Detections with Vision Foundation Models [68.90917438865078]
  Deepfake techniques for facial synthesis and editing pose serious risks for generative models.<n>In this paper, we investigate how detection performance varies across model backbones, types, and datasets.<n>We introduce Contrastive Blur, which enhances performance on facial images, and MINDER, which addresses noise type bias, balancing performance across domains.
  arXiv  Detail & Related papers  (2024-11-28T13:04:45Z)
• Addressing Vulnerabilities in AI-Image Detection: Challenges and Proposed Solutions [0.0]
  This study evaluates the effectiveness of convolutional neural networks (CNNs) and DenseNet architectures for detecting AI-generated images.<n>We analyze the impact of updates and modifications such as Gaussian blurring, prompt text changes, and Low-Rank Adaptation (LoRA) on detection accuracy.<n>The findings highlight vulnerabilities in current detection methods and propose strategies to enhance the robustness and reliability of AI-image detection systems.
  arXiv  Detail & Related papers  (2024-11-26T06:35:26Z)
• StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Model [62.25424831998405]
  StealthDiffusion is a framework that modifies AI-generated images into high-quality, imperceptible adversarial examples. It is effective in both white-box and black-box settings, transforming AI-generated images into high-quality adversarial forgeries.
  arXiv  Detail & Related papers  (2024-08-11T01:22:29Z)
• 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)
• Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model [61.53213964333474]
  We propose a unified framework Adv-Diffusion that can generate imperceptible adversarial identity perturbations in the latent space but not the raw pixel space. Specifically, we propose the identity-sensitive conditioned diffusion generative model to generate semantic perturbations in the surroundings. The designed adaptive strength-based adversarial perturbation algorithm can ensure both attack transferability and stealthiness.
  arXiv  Detail & Related papers  (2023-12-18T15:25:23Z)
• Confidence-Aware and Self-Supervised Image Anomaly Localisation [7.099105239108548]
  We discuss an improved self-supervised single-class training strategy that supports the approximation of probabilistic inference with loosen feature locality constraints. Our method is integrated into several out-of-distribution (OOD) detection models and we show evidence that our method outperforms the state-of-the-art on various benchmark datasets.
  arXiv  Detail & Related papers  (2023-03-23T12:48:47Z)
• Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging [88.20869695803631]
  We show how to derive uncertainty intervals around each pixel that are guaranteed to contain the true value. We evaluate our procedure on three image-to-image regression tasks.
  arXiv  Detail & Related papers  (2022-02-10T18:59:56Z)
• Robustness via Uncertainty-aware Cycle Consistency [44.34422859532988]
  Unpaired image-to-image translation refers to learning inter-image-domain mapping without corresponding image pairs. Existing methods learn deterministic mappings without explicitly modelling the robustness to outliers or predictive uncertainty. We propose a novel probabilistic method based on Uncertainty-aware Generalized Adaptive Cycle Consistency (UGAC)
  arXiv  Detail & Related papers  (2021-10-24T15:33:21Z)
• Uncertainty-aware Generalized Adaptive CycleGAN [44.34422859532988]
  Unpaired image-to-image translation refers to learning inter-image-domain mapping in an unsupervised manner. Existing methods often learn deterministic mappings without explicitly modelling the robustness to outliers or predictive uncertainty. We propose a novel probabilistic method called Uncertainty-aware Generalized Adaptive Cycle Consistency (UGAC)
  arXiv  Detail & Related papers  (2021-02-23T15:22:35Z)
• The Hidden Uncertainty in a Neural Networks Activations [105.4223982696279]
  The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data. This work investigates whether this distribution correlates with a model's epistemic uncertainty, thus indicating its ability to generalise to novel inputs.
  arXiv  Detail & Related papers  (2020-12-05T17:30:35Z)

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.