Web: http://arxiv.org/abs/2205.06154

May 13, 2022, 1:11 a.m. | Ameya Joshi, Minh Pham, Minsu Cho, Leonid Boytsov, Filipe Condessa, J. Zico Kolter, Chinmay Hegde

cs.LG updates on arXiv.org arxiv.org

Randomized smoothing (RS) has been shown to be a fast, scalable technique for
certifying the robustness of deep neural network classifiers. However, methods
based on RS require augmenting data with large amounts of noise, which leads to
significant drops in accuracy. We propose a training-free, modified smoothing
approach, Smooth-Reduce, that leverages patching and aggregation to provide
improved classifier certificates. Our algorithm classifies overlapping patches
extracted from an input image, and aggregates the predicted logits to certify a
larger radius around …

arxiv reduce robustness

More from arxiv.org / cs.LG updates on arXiv.org

Director, Applied Mathematics & Computational Research Division

@ Lawrence Berkeley National Lab | Berkeley, Ca

Business Data Analyst

@ MainStreet Family Care | Birmingham, AL

Assistant/Associate Professor of the Practice in Business Analytics

@ Georgetown University McDonough School of Business | Washington DC

Senior Data Science Writer

@ NannyML | Remote

Director of AI/ML Engineering

@ Armis Industries | Remote (US only), St. Louis, California

Digital Analytics Manager

@ Patagonia | Ventura, California