Analysis of Information Leakage from MCU using Neural Network

Si-Ping Gao; Yingkai Guo; Zaw Thet Aung; Yong-Xin Guo

doi:10.1109/EMCCompo.2019.8919889

Analysis of Information Leakage from MCU using Neural Network

Si-Ping Gao
, Yingkai Guo
, Zaw Thet Aung
, Yong-Xin Guo

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

1 Citation (Scopus)

Abstract

Electromagnetic leakage from an operating microcontroller unit (MCU) can be intercepted and analyzed to deduce the instructions being processed. This is helpful to understanding eavesdropping and to later protecting against it. In this work, harnessing a deep neural network, we analyze the massive electromagnetic (EM) leakage information to extract the instructions run in a microcontroller unit (MCU). An EM leakage acquisition environment is built, and the leakage signal of an MCU is collected. A multi-layer convolutional neural network is constructed for the side channel analysis and identification. The recognition accuracy is over 95% in the training phase, and more than 75% in the prediction phase. This experiment proves that the electromagnetic leakage emitted can be collected by appropriate methods and analyzed by deep learning technology. It can effectively deduce the instructions running in an MCU, which lays a foundation for the protection against eavesdropping. © 2019 IEEE.

Original language	English
Title of host publication	EMC COMPO 2019 - 2019 12th International Workshop on the Electromagnetic Compatibility of Integrated Circuits (EMC Compo)
Publisher	IEEE
Pages	171-173
ISBN (Electronic)	978-1-7281-4262-3
DOIs	https://doi.org/10.1109/EMCCompo.2019.8919889
Publication status	Published - 2019
Externally published	Yes
Event	12th International Workshop on the Electromagnetic Compatibility of Integrated Circuits, EMC COMPO 2019 - Haining, Hangzhou, China Duration: 21 Oct 2019 → 23 Oct 2019 http://emcconf.org/

Publication series

Name	EMC COMPO - International Workshop on the Electromagnetic Compatibility of Integrated Circuits

Conference

Conference	12th International Workshop on the Electromagnetic Compatibility of Integrated Circuits, EMC COMPO 2019
Place	China
City	Haining, Hangzhou
Period	21/10/19 → 23/10/19
Internet address	http://emcconf.org/

Research Keywords

deep learning
Electromagnetic leakage
instructions
microcontroller
neural network
side channel attack

Access Output

10.1109/EMCCompo.2019.8919889

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Gao, S.-P., Guo, Y., Aung, Z. T., & Guo, Y.-X. (2019). Analysis of Information Leakage from MCU using Neural Network. In EMC COMPO 2019 - 2019 12th International Workshop on the Electromagnetic Compatibility of Integrated Circuits (EMC Compo) (pp. 171-173). Article 8919889 (EMC COMPO - International Workshop on the Electromagnetic Compatibility of Integrated Circuits). IEEE. https://doi.org/10.1109/EMCCompo.2019.8919889

@inproceedings{fc190c660b514047b91f56c6e109af9c,

title = "Analysis of Information Leakage from MCU using Neural Network",

abstract = "Electromagnetic leakage from an operating microcontroller unit (MCU) can be intercepted and analyzed to deduce the instructions being processed. This is helpful to understanding eavesdropping and to later protecting against it. In this work, harnessing a deep neural network, we analyze the massive electromagnetic (EM) leakage information to extract the instructions run in a microcontroller unit (MCU). An EM leakage acquisition environment is built, and the leakage signal of an MCU is collected. A multi-layer convolutional neural network is constructed for the side channel analysis and identification. The recognition accuracy is over 95\% in the training phase, and more than 75\% in the prediction phase. This experiment proves that the electromagnetic leakage emitted can be collected by appropriate methods and analyzed by deep learning technology. It can effectively deduce the instructions running in an MCU, which lays a foundation for the protection against eavesdropping. {\textcopyright} 2019 IEEE.",

keywords = "deep learning, Electromagnetic leakage, instructions, microcontroller, neural network, side channel attack",

author = "Si-Ping Gao and Yingkai Guo and Aung, \{Zaw Thet\} and Yong-Xin Guo",

year = "2019",

doi = "10.1109/EMCCompo.2019.8919889",

language = "English",

series = "EMC COMPO - International Workshop on the Electromagnetic Compatibility of Integrated Circuits",

publisher = "IEEE",

pages = "171--173",

booktitle = "EMC COMPO 2019 - 2019 12th International Workshop on the Electromagnetic Compatibility of Integrated Circuits (EMC Compo)",

address = "United States",

note = "12th International Workshop on the Electromagnetic Compatibility of Integrated Circuits, EMC COMPO 2019 ; Conference date: 21-10-2019 Through 23-10-2019",

url = "http://emcconf.org/",

}

Gao, S-P, Guo, Y, Aung, ZT & Guo, Y-X 2019, Analysis of Information Leakage from MCU using Neural Network. in EMC COMPO 2019 - 2019 12th International Workshop on the Electromagnetic Compatibility of Integrated Circuits (EMC Compo)., 8919889, EMC COMPO - International Workshop on the Electromagnetic Compatibility of Integrated Circuits, IEEE, pp. 171-173, 12th International Workshop on the Electromagnetic Compatibility of Integrated Circuits, EMC COMPO 2019, Haining, Hangzhou, China, 21/10/19. https://doi.org/10.1109/EMCCompo.2019.8919889

Analysis of Information Leakage from MCU using Neural Network. / Gao, Si-Ping; Guo, Yingkai; Aung, Zaw Thet et al.
EMC COMPO 2019 - 2019 12th International Workshop on the Electromagnetic Compatibility of Integrated Circuits (EMC Compo). IEEE, 2019. p. 171-173 8919889 (EMC COMPO - International Workshop on the Electromagnetic Compatibility of Integrated Circuits).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Analysis of Information Leakage from MCU using Neural Network

AU - Gao, Si-Ping

AU - Guo, Yingkai

AU - Aung, Zaw Thet

AU - Guo, Yong-Xin

PY - 2019

Y1 - 2019

N2 - Electromagnetic leakage from an operating microcontroller unit (MCU) can be intercepted and analyzed to deduce the instructions being processed. This is helpful to understanding eavesdropping and to later protecting against it. In this work, harnessing a deep neural network, we analyze the massive electromagnetic (EM) leakage information to extract the instructions run in a microcontroller unit (MCU). An EM leakage acquisition environment is built, and the leakage signal of an MCU is collected. A multi-layer convolutional neural network is constructed for the side channel analysis and identification. The recognition accuracy is over 95% in the training phase, and more than 75% in the prediction phase. This experiment proves that the electromagnetic leakage emitted can be collected by appropriate methods and analyzed by deep learning technology. It can effectively deduce the instructions running in an MCU, which lays a foundation for the protection against eavesdropping. © 2019 IEEE.

AB - Electromagnetic leakage from an operating microcontroller unit (MCU) can be intercepted and analyzed to deduce the instructions being processed. This is helpful to understanding eavesdropping and to later protecting against it. In this work, harnessing a deep neural network, we analyze the massive electromagnetic (EM) leakage information to extract the instructions run in a microcontroller unit (MCU). An EM leakage acquisition environment is built, and the leakage signal of an MCU is collected. A multi-layer convolutional neural network is constructed for the side channel analysis and identification. The recognition accuracy is over 95% in the training phase, and more than 75% in the prediction phase. This experiment proves that the electromagnetic leakage emitted can be collected by appropriate methods and analyzed by deep learning technology. It can effectively deduce the instructions running in an MCU, which lays a foundation for the protection against eavesdropping. © 2019 IEEE.

KW - deep learning

KW - Electromagnetic leakage

KW - instructions

KW - microcontroller

KW - neural network

KW - side channel attack

UR - https://www.scopus.com/pages/publications/85077955281

UR - https://www.scopus.com/pages/publications/85077955281#tab=impact

U2 - 10.1109/EMCCompo.2019.8919889

DO - 10.1109/EMCCompo.2019.8919889

M3 - RGC 32 - Refereed conference paper (with host publication)

T3 - EMC COMPO - International Workshop on the Electromagnetic Compatibility of Integrated Circuits

SP - 171

EP - 173

BT - EMC COMPO 2019 - 2019 12th International Workshop on the Electromagnetic Compatibility of Integrated Circuits (EMC Compo)

PB - IEEE

T2 - 12th International Workshop on the Electromagnetic Compatibility of Integrated Circuits, EMC COMPO 2019

Y2 - 21 October 2019 through 23 October 2019

ER -

Gao SP, Guo Y, Aung ZT, Guo YX. Analysis of Information Leakage from MCU using Neural Network. In EMC COMPO 2019 - 2019 12th International Workshop on the Electromagnetic Compatibility of Integrated Circuits (EMC Compo). IEEE. 2019. p. 171-173. 8919889. (EMC COMPO - International Workshop on the Electromagnetic Compatibility of Integrated Circuits). Epub 2019 Dec 5. doi: 10.1109/EMCCompo.2019.8919889

Analysis of Information Leakage from MCU using Neural Network

Abstract

Publication series

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this