Deep neural networks are being applied in many tasks with encouraging results, and have often reached human-level performance. However, deep neural networks are vulnerable to well-designed input samples called adversarial examples. In particular, neural networks tend to misclassify adversarial examples that are imperceptible to humans. This paper introduces a new detection system that automatically detects adversarial examples on deep neural networks. Our proposed system can mostly distinguish adversarial samples and benign images in an end-to-end manner without human intervention. We exploit the important role of the frequency domain in adversarial samples and propose a method that detects malicious samples in observations. When evaluated on two standard benchmark datasets (MNIST and ImageNet), our method achieved an out-detection rate of 99.7 - 100% in many settings.
@article{arxiv.1908.01469,
title = {Automated Detection System for Adversarial Examples with High-Frequency Noises Sieve},
author = {Dang Duy Thang and Toshihiro Matsui},
journal= {arXiv preprint arXiv:1908.01469},
year = {2019}
}
Comments
Appear to 11th International Symposium on Cyberspace Safety and Security CSS 2019, Guangzhou, China