The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dans le domaine de la sécurité de l'apprentissage automatique, en tant que surface d'attaque notamment pour les appareils de pointe, l'application de l'analyse de canal secondaire telle que l'analyse de corrélation puissance/électromagnétique (CPA/CEMA) se développe. Visant à évaluer la résistance aux fuites des paramètres du modèle de réseau neuronal (NN), c'est-à-dire poids et à la biais, nous avons mené une étude de faisabilité du CPA/CEMA sur les opérations en virgule flottante (FP), qui sont les opérations de base des NN. Cet article propose des approches pour récupérer les poids et les biais en utilisant respectivement CPA/CEMA sur les opérations de multiplication et d'addition. Il est essentiel de prendre en compte les caractéristiques de la représentation IEEE 754 afin de réaliser la récupération avec une grande précision et efficacité. Nous montrons que le CPA/CEMA sur les opérations FP nécessite des approches différentes de celles du CPA/CEMA traditionnel sur les implémentations cryptographiques telles que l'AES.
Hanae NOZAKI
National Institute of Advanced Industrial Science and Technology (AIST)
Kazukuni KOBARA
National Institute of Advanced Industrial Science and Technology (AIST)
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Hanae NOZAKI, Kazukuni KOBARA, "Power Analysis of Floating-Point Operations for Leakage Resistance Evaluation of Neural Network Model Parameters" in IEICE TRANSACTIONS on Fundamentals,
vol. E107-A, no. 3, pp. 331-343, March 2024, doi: 10.1587/transfun.2023CIP0012.
Abstract: In the field of machine learning security, as one of the attack surfaces especially for edge devices, the application of side-channel analysis such as correlation power/electromagnetic analysis (CPA/CEMA) is expanding. Aiming to evaluate the leakage resistance of neural network (NN) model parameters, i.e. weights and biases, we conducted a feasibility study of CPA/CEMA on floating-point (FP) operations, which are the basic operations of NNs. This paper proposes approaches to recover weights and biases using CPA/CEMA on multiplication and addition operations, respectively. It is essential to take into account the characteristics of the IEEE 754 representation in order to realize the recovery with high precision and efficiency. We show that CPA/CEMA on FP operations requires different approaches than traditional CPA/CEMA on cryptographic implementations such as the AES.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2023CIP0012/_p
Copier
@ARTICLE{e107-a_3_331,
author={Hanae NOZAKI, Kazukuni KOBARA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Power Analysis of Floating-Point Operations for Leakage Resistance Evaluation of Neural Network Model Parameters},
year={2024},
volume={E107-A},
number={3},
pages={331-343},
abstract={In the field of machine learning security, as one of the attack surfaces especially for edge devices, the application of side-channel analysis such as correlation power/electromagnetic analysis (CPA/CEMA) is expanding. Aiming to evaluate the leakage resistance of neural network (NN) model parameters, i.e. weights and biases, we conducted a feasibility study of CPA/CEMA on floating-point (FP) operations, which are the basic operations of NNs. This paper proposes approaches to recover weights and biases using CPA/CEMA on multiplication and addition operations, respectively. It is essential to take into account the characteristics of the IEEE 754 representation in order to realize the recovery with high precision and efficiency. We show that CPA/CEMA on FP operations requires different approaches than traditional CPA/CEMA on cryptographic implementations such as the AES.},
keywords={},
doi={10.1587/transfun.2023CIP0012},
ISSN={1745-1337},
month={March},}
Copier
TY - JOUR
TI - Power Analysis of Floating-Point Operations for Leakage Resistance Evaluation of Neural Network Model Parameters
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 331
EP - 343
AU - Hanae NOZAKI
AU - Kazukuni KOBARA
PY - 2024
DO - 10.1587/transfun.2023CIP0012
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E107-A
IS - 3
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - March 2024
AB - In the field of machine learning security, as one of the attack surfaces especially for edge devices, the application of side-channel analysis such as correlation power/electromagnetic analysis (CPA/CEMA) is expanding. Aiming to evaluate the leakage resistance of neural network (NN) model parameters, i.e. weights and biases, we conducted a feasibility study of CPA/CEMA on floating-point (FP) operations, which are the basic operations of NNs. This paper proposes approaches to recover weights and biases using CPA/CEMA on multiplication and addition operations, respectively. It is essential to take into account the characteristics of the IEEE 754 representation in order to realize the recovery with high precision and efficiency. We show that CPA/CEMA on FP operations requires different approaches than traditional CPA/CEMA on cryptographic implementations such as the AES.
ER -