mlsanityData to 7 Oct 2026

Dynamic Perturbation-Adaptive Adversarial Training on Medical Image Classification

arXiv 2403.06798 ↗First posted 11 Mar 2024eess.IV cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data, raising serious concerns on network robustness. Although adversarial training (AT), in responding to malevolent AEs, was recognized as an effective approach to improve robustness, it was challenging to overcome generalization decline of networks caused by the AT. In this paper, in order to reserve high generalization while improving robustness, we proposed a dynamic perturbation-adaptive adversarial training (DPAAT) method, which placed AT in a dynamic learning environment to generate adaptive data-level perturbations and provided a dynamically updated criterion by loss information collections to handle the disadvantage of fixed perturbation sizes in conventional AT methods and the dependence on external transference. Comprehensive testing on dermatology HAM10000 dataset showed that the DPAAT not only achieved better robustness improvement and generalization preservation but also significantly enhanced mean average precision and interpretability on various CNNs, indicating its great potential as a generic adversarial training method on the MIC.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 33 references that are in the map. First posted on arXiv 11 Mar 2024.

Builds on

18 of 33 references.

References · 18

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2018Robustness May Be at Odds with Accuracycited by 873
  6. 2020A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promisescited by 230
  7. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  8. 2020Learnable Boundary Guided Adversarial Trainingcited by 93
  9. 2017Unsupervised Reverse Domain Adaptation for Synthetic Medical Images via Adversarial Trainingcited by 57
  10. 2019Instance adaptive adversarial training: Improved accuracy tradeoffs in neural netscited by 55
  11. 2021Single Model Deep Learning on Imbalanced Small Datasets for Skin Lesion Classificationcited by 23
  12. 2020Miss the Point: Targeted Adversarial Attack on Multiple Landmark Detectioncited by 21
6 more
  1. 2020Melanoma Detection using Adversarial Training and Deep Transfer Learningcited by 17
  2. 2021Soft-Attention Improves Skin Cancer Classification Performancecited by 15
  3. 2020Improving Interpretability in Medical Imaging Diagnosis using Adversarial Trainingcited by 9
  4. 2015Robust Kalman Filtering under Model Perturbationscited by 4
  5. 2022Adaptive Adversarial Training to Improve Adversarial Robustness of DNNs for Medical Image Segmentation and Detectioncited by 4
  6. 2021Adaptive perturbation adversarial training: based on reinforcement learningcited by 1

Built on by

Not cited yet.