ME-Net: Towards effective adversarial robustness with matrix estimation
Name
1905.11971.pdf
Description
Accepted version
Size
8.33 MB
Format
Unknown
Checksum (MD5)
2edf741ed89a039f27da79dc51defda7
Author(s)
Yang, Yuzhe
Zhang, Guo
Katabi, Dina
Xu, Zhi
Date Issued
2019
Journal
36th International Conference on Machine Learning, ICML 2019
Version
Author's final manuscript
Abstract
Copyright © 2019 ASME Deep neural networks are vulnerable to adversarial attacks. The literature is rich with algorithms that can easily craft successful adversarial examples. In contrast, the performance of defense techniques still lags behind. This paper proposes ME-Net, a defense method that leverages matrix estimation (ME). In ME-Net, images are preprocessed using two steps: first pixels are randomly dropped from the image; then, the image is reconstructed using ME. We show that this process destroys the adversarial structure of the noise, while rc-enforcing the global structure in the original image. Since humans typically rely on such global structures in classifying images, the process makes the network mode compatible with human perception. We conduct comprehensive experiments on prevailing benchmarks such as MNIST, CIFAR-10, SVHN, and Tiny-ImageNet. Comparing ME-Net with state-of-the-art defense mechanisms shows that ME-Net consistently outperforms prior techniques, improving robustness against both black-box and white-box attacks.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
http://proceedings.mlr.press/v97/yang19e.html
