[Resource Topic] 2023/1219: A Note on “Secure Quantized Training for Deep Learning”

Welcome to the resource topic for 2023/1219

Title:
A Note on “Secure Quantized Training for Deep Learning”

Authors: Marcel Keller, Ke Sun

Abstract:

Keller and Sun (ICML’22) have found a gap in the accuracy between floating-point deep learning in cleartext and secure quantized deep learning using multi-party computation. We have discovered that this gap is caused by a bug in the implementation of max-pooling. In this note, we present updated figures to support this conclusion. We also add figures for another network on CIFAR-10.

ePrint: https://eprint.iacr.org/2023/1219

See all topics related to this paper.

Feel free to post resources that are related to this paper below.

Example resources include: implementations, explanation materials, talks, slides, links to previous discussions on other websites.

For more information, see the rules for Resource Topics .