发表机构
Missouri University of Science & Technology; University of Houston; Cranium AI, Inc.（密苏里科学技术大学; 休斯顿大学; 颅人工智能公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出分层通道堆叠（HCS）框架，将CNN中间激活转为结构化60维表示，在涵盖GAN和扩散生成器的基准测试中获86.7%准确率，可用于AI生成图像检测及相关证据整合机制研究。
AI 中文摘要
许多合成图像检测器能做出准确预测，但对这些决策的形成过程缺乏足够解释。本文提出分层通道堆叠（Hierarchical Channel Stacking, HCS），这是一种用于AI生成图像检测的紧凑框架，它将卷积神经网络（CNN）的中间激活转换为在三个逐步加深的骨干阶段上组织的结构化60维表示。HCS使用逐通道的一级分类器和二级聚合器生成图像级预测，同时保留用于分析的显式分层结构。在涵盖生成对抗网络（GAN）和扩散模型生成器的基准测试中，HCS在留出的测试集上达到了86.7%的准确率和86.7%的宏F1值。阶段消融实验表明，完整的三阶段系统优于简化的单阶段和两阶段变体，说明分层结构携带互补的预测信息。阶段级贡献分析进一步显示，在所分析的检测器设置中，假GAN图像和假扩散图像表现出不同的阶段级贡献特征。这些结果表明，HCS不仅是一种紧凑的检测器，还是一种用于研究合成图像检测器如何在表示层级间整合证据的结构化框架。
英文摘要
Many synthetic-image detectors produce accurate predictions but offer limited insight into how those decisions are formed. This paper introduces Hierarchical Channel Stacking (HCS), a compact framework for AI-generated image detection that converts intermediate CNN activations into a structured 60-dimensional representation organized across three progressively deeper backbone stages. HCS uses per-channel Level-1 classifiers and a Level-2 aggregator to produce image-level predictions while preserving explicit hierarchical structure for analysis. On a benchmark spanning GAN and diffusion generators, HCS achieves 86.7% accuracy and 86.7% macro-F1 on the held-out test set. Stage ablation shows that the full three-stage system outperforms reduced single-stage and two-stage variants, indicating that the hierarchy carries complementary predictive information. Stage-level contribution analysis further shows that, in the analyzed detector setting, fake GAN and fake diffusion images exhibit distinct stage-level contribution profiles. These results position HCS not simply as a compact detector, but as a structured framework for studying how synthetic-image detectors assemble evidence across representation levels.
CommentsWithdrawn due to insufficient consent approval
