提出固定阈值评估方法，真实反映AI图像检测器在压缩等后处理下的性能表现。
Fixed-Threshold Evaluation of a Hybrid CNN-ViT for AI-Generated Image Detection Across Photos and Art
- 采用固定阈值评估，避免因每种后处理重新调参导致的性能虚高。
- 混合模型在艺术图像上达到98.3%准确率，照片类下降至91.4%。
- 揭示频域增强的CNN在压缩下性能暴跌，而ViT更依赖语义识别更稳定。
AI图像生成涵盖逼真照片与风格化艺术，需具备对常见后处理（如JPEG压缩、模糊、缩放）鲁棒的检测器。现有方法仅优化单一指标，忽视部署关键因素如阈值选择与固定阈值鲁棒性。本文提出固定阈值评估协议：在干净验证集上选定一次决策阈值，后续所有后处理条件下保持不变。传统方法每种条件重调阈值，人为抬高鲁棒性估计并掩盖部署失败。我们系统测试轻量级CNN-ViT混合模型（带门控融合与可选频域增强），在三个操作点（低假阳性率、ROC最优、最佳F1）下报告真实性能。结果揭示出可验证的伪造-语义谱：频域增强的CNN在纯照片上表现优异（93.33%→61.49%），但压缩后崩溃；而ViT仅轻微下降（92.86%→88.36%），凭借鲁棒语义识别能力。多种子实验显示，所有架构在艺术内容上均比逼真图像高15% AUROC（0.901–0.907 vs 0.747–0.759），证实语义模式比伪造痕迹更可靠。混合模型实现跨领域平衡：在tiny-genimage照片上达91.4%，在AiArtData艺术/图形上89.7%，在CIFAKE上98.3%（具竞争力）。固定阈值评估消除重调带来的性能膨胀，暴露真实鲁棒性差距，提供可操作部署建议：清洁照片用CNN，压缩内容用ViT，艺术/图形筛查用混合模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。