Please use this identifier to cite or link to this item:
Title: Practical side-channel based model extraction attack on tree-based machine learning algorithm
Authors: Jap, Dirmanto
Yli-Mäyry, Ville
Ito, Akira
Ueno, Rei
Bhasin, Shivam
Homma, Naofumi
Keywords: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Issue Date: 2020
Source: Jap, D., Yli-Mäyry, V., Ito, A., Ueno, R., Bhasin, S. & Homma, N. (2020). Practical side-channel based model extraction attack on tree-based machine learning algorithm. 1st ACNS Workshop on Artificial Intelligence in Hardware Security (AIHWS 2020), LNCS 12418, 93-105.
Abstract: Machine learning algorithms have been widely applied to solve various type of problems and applications. Among those, decision tree based algorithms have been considered for small Internet-of-Things (IoT) implementation, due to their simplicity. It has been shown in a recent publication, that Bonsai, a small tree-based algorithm, can be successfully fitted in a small 8-bit microcontroller. However, the security of machine learning algorithm has also been a major concern, especially with the threat of secret parameter recovery which could lead to breach of privacy. With machine learning taking over a significant proportion of industrial tasks, the security issue has become a matter of concern. Recently, secret parameter recovery for neural network based algorithm using physical side-channel leakage has been proposed. In the paper, we investigate the security of widely used decision tree algorithms running on ARM Cortex M3 platform against electromagnetic (EM) side-channel attacks. We show that by focusing on each building block function or component, one could perform divide-and-conquer approach to recover the secret parameters. To demonstrate the attack, we first report the recovery of secret parameters of Bonsai, such as, sparse projection parameters, branching function and node predictors. After the recovery of these parameters, the attacker can then reconstruct the whole architecture.
ISBN: 9783030616373
DOI: 10.1007/978-3-030-61638-0_6
Rights: © 2020 Springer Nature Switzerland AG. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:TL Conference Papers

Citations 50

Updated on Nov 25, 2022

Page view(s)

Updated on Nov 25, 2022

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.