Secure Diagnostics: Adversarial Robustness Meets Clinical Interpretability
Not on the map. Why?
Abstract (arXiv)
Deep neural networks for medical image classification often fail to generalize consistently in clinical practice due to violations of the i.i.d. assumption and opaque decision-making. This paper examines interpretability in deep neural networks fine-tuned for fracture detection by evaluating model performance against adversarial attack and comparing interpretability methods to fracture regions annotated by an orthopedic surgeon. Our findings prove that robust models yield explanations more aligned with clinically meaningful areas, indicating that robustness encourages anatomically relevant feature prioritization. We emphasize the value of interpretability for facilitating human-AI collaboration, in which models serve as assistants under a human-in-the-loop paradigm: clinically plausible explanations foster trust, enable error correction, and discourage reliance on AI for high-stakes decisions. This paper investigates robustness and interpretability as complementary benchmarks for bridging the gap between benchmark performance and safe, actionable clinical deployment.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 53 references that are in the map. First posted on arXiv 7 Apr 2025.
Builds on
28 of 53 references.
References · 28
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2017Axiomatic Attribution for Deep Networkscited by 3,384
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
- 2013Visualizing and Understanding Convolutional Networkscited by 2,290
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
- 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
- 2018Robustness May Be at Odds with Accuracycited by 880
- 2020Captum: A unified and generic model interpretability library for PyTorchcited by 547
- 2017Deep Learning for Medical Image Analysiscited by 401
16 more
- 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
- 2023A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinkingcited by 85
- 2019On the Connection Between Adversarial Robustness and Saliency Map Interpretabilitycited by 80
- 2023Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Modelscited by 79
- 2022A Light Recipe to Train Robust Vision Transformerscited by 64
- 2020Adversarial Attack Vulnerability of Medical Image Analysis Systems: Unexplored Factorscited by 40
- 2022Explainable Deep Learning Methods in Medical Image Classification: A Surveycited by 32
- 2024Demographic Bias of Expert-Level Vision-Language Foundation Models in Medical Imagingcited by 24
- 2024MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsificationcited by 21
- 2023Is Grad-CAM Explainable in Medical Images?cited by 10
- 2024Characterizing Model Robustness via Natural Input Gradientscited by 6
- 2025A Survey on Human-Centered Evaluation of Explainable AI Methods in Clinical Decision Support Systemscited by 3
- 2020Towards Trainable Saliency Maps in Medical Imagingcited by 2
- 2025Examining the Threat Landscape: Foundation Models and Model Stealingcited by 2
- 2024ULTra: Unveiling Latent Token Interpretability in Transformer-Based Understanding and Segmentationcited by 1
- 2024Enhancing Skin Cancer Diagnosis (SCD) Using Late Discrete Wavelet Transform (DWT) and New Swarm-Based Optimizerscited by 1
Built on by
Not cited yet.