Increasing-Margin Adversarial (IMA) Training to Improve Adversarial Robustness of Neural Networks

05/19/2020
by   Linhai Ma, et al.
0

Convolutional neural network (CNN) has surpassed traditional methods for med-ical image classification. However, CNN is vulnerable to adversarial attacks which may lead to disastrous consequences in medical applications. Although adversarial noises are usually generated by attack algorithms, white-noise-induced adversarial samples can exist, and therefore the threats are real. In this study, we propose a novel training method, named IMA, to improve the robust-ness of CNN against adversarial noises. During training, the IMA method in-creases the margins of training samples in the input space, i.e., moving CNN de-cision boundaries far away from the training samples to improve robustness. The IMA method is evaluated on four publicly available datasets under strong 100-PGD white-box adversarial attacks, and the results show that the proposed meth-od significantly improved CNN classification accuracy on noisy data while keep-ing a relatively high accuracy on clean data. We hope our approach may facilitate the development of robust applications in medical field.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset