On use of deep learning for side channel evaluation of black box hardware AES engine

With the increasing demand for security and privacy, there has been an increasing availability of cryptographic acclerators out of the box in modern microcontrollers, These accelerators are optimised and often black box. Thus, proper evaluation against vulnerabilities like side-channel attacks is a...

Full description

Saved in:
Bibliographic Details
Main Authors: Won, Yoo-Seung, Bhasin, Shivam
Other Authors: 7th EAI International Conference on Industrial Networks and Intelligent Systems (INISCOM 2021)
Format: Conference or Workshop Item
Language:English
Published: 2021
Subjects:
Online Access:https://hdl.handle.net/10356/147152
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-147152
record_format dspace
spelling sg-ntu-dr.10356-1471522021-08-28T20:11:18Z On use of deep learning for side channel evaluation of black box hardware AES engine Won, Yoo-Seung Bhasin, Shivam 7th EAI International Conference on Industrial Networks and Intelligent Systems (INISCOM 2021) Temasek Laboratories Engineering::Computer science and engineering Hardware AES Engine Side-channel Analysis Deep Learning With the increasing demand for security and privacy, there has been an increasing availability of cryptographic acclerators out of the box in modern microcontrollers, These accelerators are optimised and often black box. Thus, proper evaluation against vulnerabilities like side-channel attacks is a challenge in absence of architecture information and thus leakage model. In this paper, we show the use of deep learning based side-channel attack can overcome this challenge, allowing evaluation of black box AES hardware engine on a secure microcontroller, without the knowledge of precise leakage model information. Our results report full key recovery with only 3,000 traces under a profiling setting. Accepted version We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan XP GPU used for this research. 2021-08-26T02:20:43Z 2021-08-26T02:20:43Z 2021 Conference Paper Won, Y. & Bhasin, S. (2021). On use of deep learning for side channel evaluation of black box hardware AES engine. 7th EAI International Conference on Industrial Networks and Intelligent Systems (INISCOM 2021), 379, 185-194. https://dx.doi.org/10.1007/978-3-030-77424-0_15 978-3-030-77423-3 1867-8211 https://hdl.handle.net/10356/147152 10.1007/978-3-030-77424-0_15 379 185 194 en © 2021 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering. All rights reserved. This paper was published by Springer Nature Switzerland AG in Proceedings of 7th EAI International Conference on Industrial Networks and Intelligent Systems (INISCOM 2021) and is made available with permission of ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Hardware AES Engine
Side-channel Analysis
Deep Learning
spellingShingle Engineering::Computer science and engineering
Hardware AES Engine
Side-channel Analysis
Deep Learning
Won, Yoo-Seung
Bhasin, Shivam
On use of deep learning for side channel evaluation of black box hardware AES engine
description With the increasing demand for security and privacy, there has been an increasing availability of cryptographic acclerators out of the box in modern microcontrollers, These accelerators are optimised and often black box. Thus, proper evaluation against vulnerabilities like side-channel attacks is a challenge in absence of architecture information and thus leakage model. In this paper, we show the use of deep learning based side-channel attack can overcome this challenge, allowing evaluation of black box AES hardware engine on a secure microcontroller, without the knowledge of precise leakage model information. Our results report full key recovery with only 3,000 traces under a profiling setting.
author2 7th EAI International Conference on Industrial Networks and Intelligent Systems (INISCOM 2021)
author_facet 7th EAI International Conference on Industrial Networks and Intelligent Systems (INISCOM 2021)
Won, Yoo-Seung
Bhasin, Shivam
format Conference or Workshop Item
author Won, Yoo-Seung
Bhasin, Shivam
author_sort Won, Yoo-Seung
title On use of deep learning for side channel evaluation of black box hardware AES engine
title_short On use of deep learning for side channel evaluation of black box hardware AES engine
title_full On use of deep learning for side channel evaluation of black box hardware AES engine
title_fullStr On use of deep learning for side channel evaluation of black box hardware AES engine
title_full_unstemmed On use of deep learning for side channel evaluation of black box hardware AES engine
title_sort on use of deep learning for side channel evaluation of black box hardware aes engine
publishDate 2021
url https://hdl.handle.net/10356/147152
_version_ 1709685341307273216