A Thorough Comparison Study on Adversarial Attacks and Defenses for Common Thorax Disease Classification in Chest X-rays
arXiv:2003.13969
Abstract
Recently, deep neural networks (DNNs) have made great progress on automated diagnosis with chest X-rays images. However, DNNs are vulnerable to adversarial examples, which may cause misdiagnoses to patients when applying the DNN based methods in disease detection. Recently, there is few comprehensive studies exploring the influence of attack and defense methods on disease detection, especially for the multi-label classification problem. In this paper, we aim to review various adversarial attack and defense methods on chest X-rays. First, the motivations and the mathematical representations of attack and defense methods are introduced in details. Second, we evaluate the influence of several state-of-the-art attack and defense methods for common thorax disease classification in chest X-rays. We found that the attack and defense methods have poor performance with excessive iterations and large perturbations. To address this, we propose a new defense method that is robust to different degrees of perturbations. This study could provide new insights into methodological development for the community.
References in corpus (14)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Distilling the Knowledge in a Neural Network
- Explaining and Harnessing Adversarial Examples
- Intriguing properties of neural networks
- Ensemble Adversarial Training: Attacks and Defenses
- CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
- Countering Adversarial Images using Input Transformations
- Adversarial Machine Learning at Scale
- Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
- ChestNet: A Deep Neural Network for Classification of Thoracic Diseases on Chest Radiography
- NAT: Neural Architecture Transformer for Accurate and Compact Architectures
- A New Defense Against Adversarial Images: Turning a Weakness into a Strength
- Early Diagnosis of Pneumonia with Deep Learning
- Improving the Robustness of Deep Neural Networks via Adversarial Training with Triplet Loss