Fixed-Threshold Evaluation of a Hybrid CNN-ViT for AI-Generated Image Detection Across Photos and Art

• URL: http://arxiv.org/abs/2512.21512v1
• Date: Thu, 25 Dec 2025 05:19:09 GMT
• Title: Fixed-Threshold Evaluation of a Hybrid CNN-ViT for AI-Generated Image Detection Across Photos and Art
• Authors: Md Ashik Khan, Arafat Alam Jion,
• Abstract summary: We introduce fixed-threshold evaluation that holds decision thresholds, selected once on clean validation data, fixed across all post-processing transformations.<n>Our hybrid approach achieves balanced crossdomain performance: 91.4% accuracy on tinygenimage photos, 89.7% accuracy on AiData art/graphics, and 98.3% (competitive) on CIFAKE.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: AI image generators create both photorealistic images and stylized art, necessitating robust detectors that maintain performance under common post-processing transformations (JPEG compression, blur, downscaling). Existing methods optimize single metrics without addressing deployment-critical factors such as operating point selection and fixed-threshold robustness. This work addresses misleading robustness estimates by introducing a fixed-threshold evaluation protocol that holds decision thresholds, selected once on clean validation data, fixed across all post-processing transformations. Traditional methods retune thresholds per condition, artificially inflating robustness estimates and masking deployment failures. We report deployment-relevant performance at three operating points (Low-FPR, ROC-optimal, Best-F1) under systematic degradation testing using a lightweight CNN-ViT hybrid with gated fusion and optional frequency enhancement. Our evaluation exposes a statistically validated forensic-semantic spectrum: frequency-aided CNNs excel on pristine photos but collapse under compression (93.33% to 61.49%), whereas ViTs degrade minimally (92.86% to 88.36%) through robust semantic pattern recognition. Multi-seed experiments demonstrate that all architectures achieve 15% higher AUROC on artistic content (0.901-0.907) versus photorealistic images (0.747-0.759), confirming that semantic patterns provide fundamentally more reliable detection cues than forensic artifacts. Our hybrid approach achieves balanced cross-domain performance: 91.4% accuracy on tiny-genimage photos, 89.7% on AiArtData art/graphics, and 98.3% (competitive) on CIFAKE. Fixed-threshold evaluation eliminates retuning inflation, reveals genuine robustness gaps, and yields actionable deployment guidance: prefer CNNs for clean photo verification, ViTs for compressed content, and hybrids for art/graphics screening.

Related papers

• ForensicFormer: Hierarchical Multi-Scale Reasoning for Cross-Domain Image Forgery Detection [0.0]
  ForensicFormer is a hierarchical framework that unifies low-level artifact detection, mid-level boundary analysis, and high-level semantic reasoning.<n>Our method maintains 86.8% average accuracy across seven diverse test sets, spanning traditional manipulations, GAN-generated images, and diffusion model outputs.
  arXiv  Detail & Related papers  (2026-01-12T04:29:36Z)
• Detection of AI Generated Images Using Combined Uncertainty Measures and Particle Swarm Optimised Rejection Mechanism [1.8718443774434668]
  This paper presents a robust detection framework that leverages multiple uncertainty measures to decide whether to trust or reject a model's predictions.<n>We focus on three complementary techniques: Fisher Information, entropy-based uncertainty from Monte Carlo Dropout, and predictive variance from a Deep Kernel Learning framework.<n>Results demonstrate that multi-source uncertainty fusion provides a resilient and adaptive solution for AI-generated image detection.
  arXiv  Detail & Related papers  (2025-12-20T22:47:42Z)
• Stylized Synthetic Augmentation further improves Corruption Robustness [4.206961078715932]
  This paper proposes a training data augmentation pipeline that combines synthetic image data with neural style transfer.<n>We show that although applying style transfer on synthetic images degrades their quality with respect to the common Frechet Inception Distance metric, these images are surprisingly beneficial for model training.
  arXiv  Detail & Related papers  (2025-12-17T18:28:04Z)
• On the Problem of Consistent Anomalies in Zero-Shot Industrial Anomaly Detection [0.0]
  We introduce Consistent-Anomaly Detection Graph (CoDeGraph), a novel algorithm that identifies and filters consistent anomalies from similarity computations.<n>CoDeGraph constructs an image-level graph, with images as nodes and edges connecting those with shared consistent-anomaly patterns.<n>Experiments on MVTec AD with the ViT-L-14-336 backbone achieve 98.3% AUROC for AC and AS performance of 66.8%.
  arXiv  Detail & Related papers  (2025-10-12T05:28:28Z)
• Edge-Enhanced Vision Transformer Framework for Accurate AI-Generated Image Detection [0.0]
  We propose a hybrid detection framework that combines a fine-tuned Vision Transformer (ViT) with a novel edge-based image processing module.<n>The proposed method is highly suitable for real-world applications in automated content verification and digital forensics.
  arXiv  Detail & Related papers  (2025-08-25T10:30:56Z)
• GRASP-PsONet: Gradient-based Removal of Spurious Patterns for PsOriasis Severity Classification [0.0]
  We propose a framework to automatically flag problematic training images that introduce spurious correlations.<n>Removing 8.2% of flagged images improves model AUC-ROC by 5% (85% to 90%) on a held out test set.<n>When applied to a subset of training data rated by two dermatologists, the method identifies over 90% of cases with inter-rater disagreement.
  arXiv  Detail & Related papers  (2025-06-27T03:42:09Z)
• CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI [58.35348718345307]
  Current efforts to distinguish between real and AI-generated images may lack generalization.<n>We propose a novel framework, Co-Spy, that first enhances existing semantic features.<n>We also create Co-Spy-Bench, a comprehensive dataset comprising 5 real image datasets and 22 state-of-the-art generative models.
  arXiv  Detail & Related papers  (2025-03-24T01:59:29Z)
• 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 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)
• (Certified!!) Adversarial Robustness for Free! [116.6052628829344]
  We certify 71% accuracy on ImageNet under adversarial perturbations constrained to be within a 2-norm of 0.5. We obtain these results using only pretrained diffusion models and image classifiers, without requiring any fine tuning or retraining of model parameters.
  arXiv  Detail & Related papers  (2022-06-21T17:27:27Z)
• To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection [95.21700830273221]
  Weakly-supervised salient object detection (WSOD) aims to develop saliency models using image-level annotations. We propose a self-calibrated training strategy by explicitly establishing a mutual calibration loop between pseudo labels and network predictions. We prove that even a much smaller dataset with well-matched annotations can facilitate models to achieve better performance as well as generalizability.
  arXiv  Detail & Related papers  (2021-09-04T02:45:22Z)
• Vision Transformers for femur fracture classification [59.99241204074268]
  The Vision Transformer (ViT) was able to correctly predict 83% of the test images. Good results were obtained in sub-fractures with the largest and richest dataset ever.
  arXiv  Detail & Related papers  (2021-08-07T10:12:42Z)

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.