English

Automated Detection System for Adversarial Examples with High-Frequency Noises Sieve

Computer Vision and Pattern Recognition 2019-08-06 v1 Machine Learning Image and Video Processing

Abstract

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.

Keywords

Cite

@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

R2 v1 2026-06-23T10:39:29.141Z