Intermediate Representations are Strong AI-Generated Image Detectors

• URL: http://arxiv.org/abs/2605.04358v1
• Date: Tue, 05 May 2026 23:26:02 GMT
• Title: Intermediate Representations are Strong AI-Generated Image Detectors
• Abstract summary: We propose a search-based method employing data sensitivity embedding in intermediate layers to detect AI-generated images.<n>Given a set of real and AI-generated images, our method examines the similarity between original image embeddings and perturbed image embeddings, and detects AI-generated images based on the similarity.<n>Our method achieves the largest performance gain on the Forensics Small benchmark by 39.61% compared to the best training-free method and 5.14% compared to the best training-based method in AUROC score.
• Score: 51.7378156094049
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid advancement in generative AI models has enabled the creation of photorealistic images. At the same time, there are growing concerns about the potential misuse and dangers of generated content, as well as a pressing need for effective AI-generated image detectors. However, current training-based detection techniques are typically computationally costly and can hardly be generalized to unseen data domains, while training-free methods fall short in detection performance. To bridge this gap, we propose a search-based method employing data embedding sensitivity in intermediate layers to detect AI-generated images. Given a set of real and AI-generated images, our method examines the similarity between original image embeddings and perturbed image embeddings, and detects AI-generated images based on the similarity. We examine the proposed method on two comprehensive benchmarks: GenImage and Forensics Small. Our method exhibits improved performance across different datasets compared to both training-free and training-based state-of-the-art methods. On average, our method achieves the largest performance gain on the Forensics Small benchmark by 39.61% compared to the best training-free method and 5.14% compared to the best training-based method in AUROC score.

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)
• Boosting Robust AIGI Detection with LoRA-based Pairwise Training [55.076681464804636]
  Current AIGI detectors perform admirably on clean datasets, but their detection performance decreases when deployed "in the wild"<n>We propose a novel Lo-based Pairwise Training (RA) strategy designed specifically to achieve robust detection for AIGI under severe distortions.
  arXiv  Detail & Related papers  (2026-04-14T05:35:32Z)
• Efficient Zero-Shot AI-Generated Image Detection [2.915868985330569]
  We propose a training-free AI-generated image detection method that measures representation sensitivity to structured frequencys.<n>The proposed method is computationally lightweight, as perturbation generation requires only a single Fourier transform for an input image.<n>Extensive experiments on challenging benchmarks demonstrate the efficacy of our method over state-of-the-art (SoTA)
  arXiv  Detail & Related papers  (2026-03-23T06:33:20Z)
• 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)
• 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)
• SAGI: Semantically Aligned and Uncertainty Guided AI Image Inpainting [11.216906046169683]
  SAGI-D is the largest and most diverse dataset of AI-generated inpaintings.<n>Our experiments show that semantic alignment significantly improves image quality and aesthetics.<n>Using SAGI-D for training several image forensic approaches increases in-domain detection performance on average by 37.4%.
  arXiv  Detail & Related papers  (2025-02-10T15:56:28Z)
• Epistemic Uncertainty for Generated Image Detection [107.62647907393377]
  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.
  arXiv  Detail & Related papers  (2024-12-08T11:32:25Z)
• 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)
• Improving Interpretability and Robustness for the Detection of AI-Generated Images [6.116075037154215]
  We analyze existing state-of-the-art AIGI detection methods based on frozen CLIP embeddings. We show how to interpret them, shedding light on how images produced by various AI generators differ from real ones.
  arXiv  Detail & Related papers  (2024-06-21T10:33:09Z)
• 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)

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.