Reverse-Engineering CNN Models Using Side-Channel Attacks

Download PDF
Open Webpage

Weizhe Hua, Zhiru Zhang, G. Edward Suh

Published: 2022, Last Modified: 15 May 2025IEEE Des. Test 2022EveryoneRevisionsBibTeXCC BY-SA 4.0
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