ModuloNET: Neural Networks Meet Modular Arithmetic for Efficient Hardware Masking
Intellectual Property (IP) thefts of trained machine learning (ML) models through side-channel attacks on inference engines are becoming a major threat. Indeed, several recent works have shown reverse engineering of the model internals using such attacks, but the research on building defenses is la...
Saved in:
Main Authors: | Anuj Dubey, Afzal Ahmad, Muhammad Adeel Pasha, Rosario Cammarota, Aydin Aysu |
---|---|
Format: | article |
Language: | EN |
Published: |
Ruhr-Universität Bochum
2021
|
Subjects: | |
Online Access: | https://doaj.org/article/9b4a0f8a04d94628a67a94e0eb278e22 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Automated Generation of Masked Hardware
by: David Knichel, et al.
Published: (2021) -
Generic Hardware Private Circuits
by: David Knichel, et al.
Published: (2021) -
Cryptanalysis of Efficient Masked Ciphers: Applications to Low Latency
by: Tim Beyne, et al.
Published: (2021) -
MIRACLE: MIcRo-ArChitectural Leakage Evaluation
by: Ben Marshall, et al.
Published: (2021) -
Masked Accelerators and Instruction Set Extensions for Post-Quantum Cryptography
by: Tim Fritzmann, et al.
Published: (2021)