Reverse-Engineering CNN Models Using Side-Channel Attacks
Lists
Only you see this
Abstract
This article demonstrates that architectural side-channel attacks (i.e., memory access patterns) can help leak the parameters of a convolutional neural network. —Jeyavijayan “JV” Rajendran, Texas A&M University
BibTeX
@inproceedings{hua2022reverse,
author = {Weizhe Hua and Zhiru Zhang and G. Edward Suh},
title = {{Reverse-Engineering CNN Models Using Side-Channel Attacks}},
booktitle = {IEEE Des. Test},
year = {2022},
url = {https://openreview.net/forum?id=d0aSC7avUH},
}Loading related content...