Saved in:
Bibliographic Details
Main Authors: Horvath, Peter, Chmielewski, Lukasz, Weissbart, Leo, Batina, Lejla, Yarom, Yuval
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.13575
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910306878357504
author Horvath, Peter
Chmielewski, Lukasz
Weissbart, Leo
Batina, Lejla
Yarom, Yuval
author_facet Horvath, Peter
Chmielewski, Lukasz
Weissbart, Leo
Batina, Lejla
Yarom, Yuval
contents Neural networks have become popular due to their versatility and state-of-the-art results in many applications, such as image classification, natural language processing, speech recognition, forecasting, etc. These applications are also used in resource-constrained environments such as embedded devices. In this work, the susceptibility of neural network implementations to reverse engineering is explored on the NVIDIA Jetson Nano microcomputer via side-channel analysis. To this end, an architecture extraction attack is presented. In the attack, 15 popular convolutional neural network architectures (EfficientNets, MobileNets, NasNet, etc.) are implemented on the GPU of Jetson Nano and the electromagnetic radiation of the GPU is analyzed during the inference operation of the neural networks. The results of the analysis show that neural network architectures are easily distinguishable using deep learning-based side-channel analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2401_13575
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CNN architecture extraction on edge GPU
Horvath, Peter
Chmielewski, Lukasz
Weissbart, Leo
Batina, Lejla
Yarom, Yuval
Cryptography and Security
Machine Learning
Neural networks have become popular due to their versatility and state-of-the-art results in many applications, such as image classification, natural language processing, speech recognition, forecasting, etc. These applications are also used in resource-constrained environments such as embedded devices. In this work, the susceptibility of neural network implementations to reverse engineering is explored on the NVIDIA Jetson Nano microcomputer via side-channel analysis. To this end, an architecture extraction attack is presented. In the attack, 15 popular convolutional neural network architectures (EfficientNets, MobileNets, NasNet, etc.) are implemented on the GPU of Jetson Nano and the electromagnetic radiation of the GPU is analyzed during the inference operation of the neural networks. The results of the analysis show that neural network architectures are easily distinguishable using deep learning-based side-channel analysis.
title CNN architecture extraction on edge GPU
topic Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2401.13575