Improving the Robustness of Deep Neural Networks via Stability Training

Preprint English OPEN
Zheng, Stephan; Song, Yang; Leung, Thomas; Goodfellow, Ian;
  • Subject: Computer Science - Computer Vision and Pattern Recognition | Computer Science - Learning

In this paper we address the issue of output instability of deep neural networks: small perturbations in the visual input can significantly distort the feature embeddings and output of a neural network. Such instability affects many deep architectures with state-of-the-... View more
  • References (1)

    [1] I. J. Goodfellow, J. Shlens, and C. Szegedy. Explaining and Harnessing Adversarial Examples. arXiv:1412.6572 [cs, stat], 2014. 1, 2

  • Metrics
Share - Bookmark