Scholarlink

<p>Deep learning models have revolutionized medical image analysis but remain vulnerable to adversarial attacks. This work presents FusionStack, an explainability-driven framework for detecting adversarial perturbations through multi-method XAI stability analysis. We introduce three novel stability metrics (LIME Stability Metric, SHAP Stability Metric, Grad-CAM Stability Metric) quantifying explanation consistency across convolutional feature hierarchies, augmented with frequency-domain and gradient-based features. Tested on five medical imaging datasets, five CNN models, and five adversarial attacks with rigorous patient-level separation, FusionStack achieves 98.71% accuracy and 0.998 AUC. Cross-attack evaluation shows DeepFool-trained detectors achieve 96.85% transferability as universal defenders. Cross-dataset evaluation demonstrates 87.05% mean accuracy, with histopathology-trained detectors achieving 100% transfer to all modalities. Lightweight frequency-domain detection (10 features) achieves 95.46% accuracy with <InlineEquation ID="IEq1"><EquationSource Format="TEX">\(5.75\times\)</EquationSource></InlineEquation> speedup. Our findings establish XAI stability analysis as a principled pathway toward adversarially robust medical AI systems for safety-critical applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Unmasking adversarial attacks using a robust XAI-driven approach for secure medical image classification

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月23日

查看全文
  • Sudarshan Saha,
  • Sohel Rana,
  • Ahmed Wasif Reza,
  • M. Ruhul Amin

摘要

Deep learning models have revolutionized medical image analysis but remain vulnerable to adversarial attacks. This work presents FusionStack, an explainability-driven framework for detecting adversarial perturbations through multi-method XAI stability analysis. We introduce three novel stability metrics (LIME Stability Metric, SHAP Stability Metric, Grad-CAM Stability Metric) quantifying explanation consistency across convolutional feature hierarchies, augmented with frequency-domain and gradient-based features. Tested on five medical imaging datasets, five CNN models, and five adversarial attacks with rigorous patient-level separation, FusionStack achieves 98.71% accuracy and 0.998 AUC. Cross-attack evaluation shows DeepFool-trained detectors achieve 96.85% transferability as universal defenders. Cross-dataset evaluation demonstrates 87.05% mean accuracy, with histopathology-trained detectors achieving 100% transfer to all modalities. Lightweight frequency-domain detection (10 features) achieves 95.46% accuracy with \(5.75\times\) speedup. Our findings establish XAI stability analysis as a principled pathway toward adversarially robust medical AI systems for safety-critical applications.