Tight certificates of adversarial robustness for randomly smoothed classifiers
Name
NeurIPS-2019-tight-certificates-of-adversarial-robustness-for-randomly-smoothed-classifiers-Paper.pdf
Description
Published version
Size
545.21 KB
Format
Adobe PDF
Checksum (MD5)
0e45c6d99b0684655975dfd74b91deee
Author(s)
Lee, Guang-He
Yuan, Yang
Jaakkola, Tommi S
Date Issued
February 2020
Journal
32nd Conference on Neural Information Processing Systems (NeurIPS 2018)
Citation
Lee, Guang-He et al. “Tight certificates of adversarial robustness for randomly smoothed classifiers.”32nd Conference on Neural Information Processing Systems, December 2018, Montreal, Canada, Neural Information Processing Systems, 2018. © 2018 The Author(s)
Version
Final published version
Abstract
Strong theoretical guarantees of robustness can be given for ensembles of classifiers generated by input randomization. Specifically, an `2 bounded adversary cannot alter the ensemble prediction generated by an additive isotropic Gaussian noise, where the radius for the adversary depends on both the variance of the distribution as well as the ensemble margin at the point of interest. We build on and considerably expand this work across broad classes of distributions. In particular, we offer adversarial robustness guarantees and associated algorithms for the discrete case where the adversary is `0 bounded. Moreover, we exemplify how the guarantees can be tightened with specific assumptions about the function class of the classifier such as a decision tree. We empirically illustrate these results with and without functional restrictions across image and molecule datasets.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/2019/hash/fa2e8c4385712f9a1d24c363a2cbe5b8-Abstract.html
