发表机构
University of Catania; State University of New York Polytechnic Institute（卡塔尼亚大学; 纽约州立大学理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
HexMIL是一种无掩码的医疗深度伪造检测器，采用分层注意力多实例学习，利用二元体积级监督实现AI篡改CT体积的事前可解释检测，在跨生成器泛化任务中性能优于基线。
AI 中文摘要
医疗深度伪造（即由深度生成模型篡改的医疗图像）的出现对临床工作流程构成重大威胁。然而，现有检测器存在两个关键局限：对未见生成架构的泛化能力差，且缺乏可解释性。在此背景下，我们提出HexMIL（分层可解释多实例学习），一种无掩码的医疗深度伪造检测器，仅利用二元体积级监督即可同时解决上述两个局限。HexMIL将每个CT体积分解为块和切片的两级层次结构，通过独立的门控注意力模块聚合，其权重直接组合为全分辨率3D注意力体积，无需任何像素级标注即可定位被篡改的子区域。与Grad-CAM等事后方法不同，HexMIL的注意力权重构成了驱动分类决策的精确前向计算，提供事前且结构忠实的空间归因。我们在M3DSynth和CT-GAN数据集上，采用严格的跨生成器泛化协议评估HexMIL：在单一生成架构上训练，在未见架构上测试。HexMIL在域外分类中比所有基线高出9.1的AUC和9.4的F1，且在定位任务中取得最佳平均IoU和指向游戏（Pointing Game）分数。项目页面：this http URL。
英文摘要
The emergence of medical deepfakes, i.e., medical images manipulated by deep generative models, poses a significant threat to clinical workflows. However, existing detectors suffer from two critical limitations: poor generalization to unseen generative architectures for manipulation detection and lack of interpretability. In this context, we present HexMIL (Hierarchical EXplainable Multiple Instance Learning), a mask-free medical deepfake detector that simultaneously addresses both limitations using only binary volume-level supervision. HexMIL decomposes each CT volume into a two-level hierarchy of patches and slices, aggregated via independent Gated Attention modules whose weights are directly combined into a full-resolution 3D attention volume that localizes the manipulated sub-region without any pixel-level annotation. Unlike post-hoc methods such as Grad-CAM, HexMIL's attention weights constitute the exact forward computation driving the classification decision, providing ante-hoc and structurally faithful spatial attribution. We evaluate HexMIL on M3DSynth and CT-GAN datasets under a rigorous cross-generator generalization protocol, training on a single generative architecture and testing on unseen ones. HexMIL outperforms all baselines by $+9.1$ AUC and $+9.4$ F1 in out-of-domain classification, and achieves the best average IoU and Pointing Game score in localization. Project page: opontorno.github.io/hexmil.
CommentsAccepted at ACM Multimedia 2026 (MM '26)
Journal refProceedings of the 34th ACM International Conference on Multimedia (MM '26), November 10--14, 2026, Rio de Janeiro, Brazil
