Multi-Dimensional Fusion Deep Learning for Side Channel Analysis
The rapid advancement of deep learning has significantly heightened the threats posed by Side-Channel Attacks (SCAs) to information security, transforming their effectiveness to a degree several orders of magnitude superior to conventional signal processing techniques. However, the majority of exist...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-11-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/12/23/4728 |
_version_ | 1797400354306916352 |
---|---|
author | Tuo Deng Huanyu Wang Dalin He Naixue Xiong Wei Liang Junnian Wang |
author_facet | Tuo Deng Huanyu Wang Dalin He Naixue Xiong Wei Liang Junnian Wang |
author_sort | Tuo Deng |
collection | DOAJ |
description | The rapid advancement of deep learning has significantly heightened the threats posed by Side-Channel Attacks (SCAs) to information security, transforming their effectiveness to a degree several orders of magnitude superior to conventional signal processing techniques. However, the majority of existing Deep-Learning Side-Channel Attacks (DLSCAs) primarily focus on the classification accuracy of the trained model at the attack stage, often assuming that adversaries have unlimited computational and time resources during the profiling stage. This might result in an inflated assessment of the trained model’s fitting capability in a real attack scenario. In this paper, we present a novel DLSCA model, called a Multi-Dimensional Fusion Convolutional Residual Dendrite (MD_CResDD) network, to enhance and speed up the feature extraction process by incorporating a multi-scale feature fusion mechanism. By testing the proposed model on two software implementations of AES-128, we show that it is feasible to improve the profiling speed by at least 34% compared to other existing deep-learning models for DLSCAs and meanwhile achieved a certain level of improvement (8.4% and 0.8% for two implementations) in the attack accuracy. Furthermore, we also investigate how different fusion approaches, fusion times, and residual blocks can affect the attack efficiency on the same two datasets. |
first_indexed | 2024-03-09T01:53:23Z |
format | Article |
id | doaj.art-ecfdea13c10848d6a3763cfbcff7c21d |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-09T01:53:23Z |
publishDate | 2023-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-ecfdea13c10848d6a3763cfbcff7c21d2023-12-08T15:13:45ZengMDPI AGElectronics2079-92922023-11-011223472810.3390/electronics12234728Multi-Dimensional Fusion Deep Learning for Side Channel AnalysisTuo Deng0Huanyu Wang1Dalin He2Naixue Xiong3Wei Liang4Junnian Wang5School of Physics and Electronic Science, Hunan University of Science and Technology, Xiangtan 411201, ChinaSchool of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201, ChinaSchool of Physics and Electronic Science, Hunan University of Science and Technology, Xiangtan 411201, ChinaSchool of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201, ChinaSchool of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201, ChinaSchool of Physics and Electronic Science, Hunan University of Science and Technology, Xiangtan 411201, ChinaThe rapid advancement of deep learning has significantly heightened the threats posed by Side-Channel Attacks (SCAs) to information security, transforming their effectiveness to a degree several orders of magnitude superior to conventional signal processing techniques. However, the majority of existing Deep-Learning Side-Channel Attacks (DLSCAs) primarily focus on the classification accuracy of the trained model at the attack stage, often assuming that adversaries have unlimited computational and time resources during the profiling stage. This might result in an inflated assessment of the trained model’s fitting capability in a real attack scenario. In this paper, we present a novel DLSCA model, called a Multi-Dimensional Fusion Convolutional Residual Dendrite (MD_CResDD) network, to enhance and speed up the feature extraction process by incorporating a multi-scale feature fusion mechanism. By testing the proposed model on two software implementations of AES-128, we show that it is feasible to improve the profiling speed by at least 34% compared to other existing deep-learning models for DLSCAs and meanwhile achieved a certain level of improvement (8.4% and 0.8% for two implementations) in the attack accuracy. Furthermore, we also investigate how different fusion approaches, fusion times, and residual blocks can affect the attack efficiency on the same two datasets.https://www.mdpi.com/2079-9292/12/23/4728side-channel attacksdeep learningmulti-scale feature fusionnetwork fusionAES-128 |
spellingShingle | Tuo Deng Huanyu Wang Dalin He Naixue Xiong Wei Liang Junnian Wang Multi-Dimensional Fusion Deep Learning for Side Channel Analysis Electronics side-channel attacks deep learning multi-scale feature fusion network fusion AES-128 |
title | Multi-Dimensional Fusion Deep Learning for Side Channel Analysis |
title_full | Multi-Dimensional Fusion Deep Learning for Side Channel Analysis |
title_fullStr | Multi-Dimensional Fusion Deep Learning for Side Channel Analysis |
title_full_unstemmed | Multi-Dimensional Fusion Deep Learning for Side Channel Analysis |
title_short | Multi-Dimensional Fusion Deep Learning for Side Channel Analysis |
title_sort | multi dimensional fusion deep learning for side channel analysis |
topic | side-channel attacks deep learning multi-scale feature fusion network fusion AES-128 |
url | https://www.mdpi.com/2079-9292/12/23/4728 |
work_keys_str_mv | AT tuodeng multidimensionalfusiondeeplearningforsidechannelanalysis AT huanyuwang multidimensionalfusiondeeplearningforsidechannelanalysis AT dalinhe multidimensionalfusiondeeplearningforsidechannelanalysis AT naixuexiong multidimensionalfusiondeeplearningforsidechannelanalysis AT weiliang multidimensionalfusiondeeplearningforsidechannelanalysis AT junnianwang multidimensionalfusiondeeplearningforsidechannelanalysis |