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 lar...

Description complète

Détails bibliographiques

Auteurs principaux:	Anuj Dubey, Afzal Ahmad, Muhammad Adeel Pasha, Rosario Cammarota, Aydin Aysu
Format:	Artigo
Langue:	Inglês
Publié:	Ruhr-Universität Bochum 2021-11-01
Collection:	Transactions on Cryptographic Hardware and Embedded Systems
Sujets:	Neural networks Side-channel attacks Hardware Masking
Accès en ligne:	https://tches.iacr.org/index.php/TCHES/article/view/9306
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!