利用病理图像层级结构提升模型抗攻击能力。
Hierarchical Self-Supervised Adversarial Training for Robust Vision Models in Histopathology
- 基于多层级对比学习构建对抗样本，融合患者-切片-局部块关系
- 白盒攻击下鲁棒性提升54.31%，黑盒攻击性能下降仅3-4%
- 适合医疗影像领域研究者与需要高可靠视觉模型的场景
对抗攻击对医疗等关键领域的视觉模型构成重大挑战，而现有方法在生物医学和显微图像中的应用仍有限。传统自监督对抗训练忽视了病理图像中患者-切片-局部块的层次结构，该结构蕴含重要判别信息。为此，我们提出层次化自监督对抗训练（HSAT），通过多级对比学习挖掘层级信号，生成更有效的对抗样本，并融入对抗训练以增强模型鲁棒性。在多分类病理数据集OpenSRH上的实验表明，HSAT优于来自生物医学与自然图像领域的现有方法：在白盒设置下平均提升54.31%的鲁棒性，黑盒设置下性能下降控制在3-4%，远低于基线25-30%的下降幅度。该工作为该领域树立了新基准，其训练与评估代码已开源。
原文摘要 · Abstract (English)
Adversarial attacks pose significant challenges for vision models in critical fields like healthcare, where reliability is essential. Although adversarial training has been well studied in natural images, its application to biomedical and microscopy data remains limited. Existing self-supervised adversarial training methods overlook the hierarchical structure of histopathology images, where patient-slide-patch relationships provide valuable discriminative signals. To address this, we propose Hierarchical Self-Supervised Adversarial Training (HSAT), which exploits these properties to craft adversarial examples using multi-level contrastive learning and integrate it into adversarial training for enhanced robustness. We evaluate HSAT on multiclass histopathology dataset OpenSRH and the results show that HSAT outperforms existing methods from both biomedical and natural image domains. HSAT enhances robustness, achieving an average gain of 54.31% in the white-box setting and reducing performance drops to 3-4% in the black-box setting, compared to 25-30% for the baseline. These results set a new benchmark for adversarial training in this domain, paving the way for more robust models. Our Code for training and evaluation is available at https://github.com/HashmatShadab/HSAT.
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。