Two sides of the same coin : boons and banes of machine learning in hardware security
The last decade has witnessed remarkable research advances at the intersection of machine learning (ML) and hardware security. The confluence of the two technologies has created many interesting and unique opportunities, but also left some issues in their wake. ML schemes have been extensively used...
Saved in:
Main Authors: | , , , , , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/155876 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-155876 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1558762022-03-25T08:11:00Z Two sides of the same coin : boons and banes of machine learning in hardware security Liu, Wenye Chang, Chip Hong Wang, Xueyang Liu, Chen Fung, Jason M. Mohammad Ebrahimabadi Karimi, Naghmeh Meng, Xingyu Basu, Kanad School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering::Computer hardware, software and systems Hardware Security Hardware Trojan Physically Unclonable Functions Edge AI Physical Attacks The last decade has witnessed remarkable research advances at the intersection of machine learning (ML) and hardware security. The confluence of the two technologies has created many interesting and unique opportunities, but also left some issues in their wake. ML schemes have been extensively used to enhance the security and trust of embedded systems like hardware Trojans and malware detection. On the other hand, ML-based approaches have also been adopted by adversaries to assist side-channel attacks, reverse engineer integrated circuits and break hardware security primitives like Physically Unclonable Functions (PUFs). Deep learning is a subfield of ML. It can continuously learn from a large amount of labeled data with a layered structure. Despite the impressive outcomes demonstrated by deep learning in many application scenarios, the dark side of it has not been fully exposed yet. The inability to fully understand and explain what has been done within the super-intelligence can turn an inherently benevolent system into malevolent. Recent research has revealed that the outputs of Deep Neural Networks (DNNs) can be easily corrupted by imperceptibly small input perturbations. As computations are brought nearer to the source of data creation, the attack surface of DNN has also been extended from the input data to the edge devices. Accordingly, due to the opportunities of ML-assisted security and the vulnerabilities of ML implementation, in this paper, we will survey the applications, vulnerabilities and fortification of ML from the perspective of hardware security. We will discuss the possible future research directions, and thereby, sharing a roadmap for the hardware security community in general. National Research Foundation (NRF) Published version This work was supported by the National Research Foundation, Singapore, through its National Cybersecurity R&D Programme/Cyber-Hardware Forensic & Assurance Evaluation R&D Programme under Award CHFA-GC1-AW01. 2022-03-25T08:11:00Z 2022-03-25T08:11:00Z 2021 Journal Article Liu, W., Chang, C. H., Wang, X., Liu, C., Fung, J. M., Mohammad Ebrahimabadi, Karimi, N., Meng, X. & Basu, K. (2021). Two sides of the same coin : boons and banes of machine learning in hardware security. IEEE Journal On Emerging and Selected Topics in Circuits and Systems, 11(2), 228-251. https://dx.doi.org/10.1109/JETCAS.2021.3084400 2156-3357 https://hdl.handle.net/10356/155876 10.1109/JETCAS.2021.3084400 2-s2.0-85107184257 2 11 228 251 en CHFA-GC1-AW01 IEEE Journal on Emerging and Selected Topics in Circuits and Systems © 2021 IEEE. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/. 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::Electrical and electronic engineering::Computer hardware, software and systems Hardware Security Hardware Trojan Physically Unclonable Functions Edge AI Physical Attacks |
spellingShingle |
Engineering::Electrical and electronic engineering::Computer hardware, software and systems Hardware Security Hardware Trojan Physically Unclonable Functions Edge AI Physical Attacks Liu, Wenye Chang, Chip Hong Wang, Xueyang Liu, Chen Fung, Jason M. Mohammad Ebrahimabadi Karimi, Naghmeh Meng, Xingyu Basu, Kanad Two sides of the same coin : boons and banes of machine learning in hardware security |
description |
The last decade has witnessed remarkable research advances at the intersection of machine learning (ML) and hardware security. The confluence of the two technologies has created many interesting and unique opportunities, but also left some issues in their wake. ML schemes have been extensively used to enhance the security and trust of embedded systems like hardware Trojans and malware detection. On the other hand, ML-based approaches have also been adopted by adversaries to assist side-channel attacks, reverse engineer integrated circuits and break hardware security primitives like Physically Unclonable Functions (PUFs). Deep learning is a subfield of ML. It can continuously learn from a large amount of labeled data with a layered structure. Despite the impressive outcomes demonstrated by deep learning in many application scenarios, the dark side of it has not been fully exposed yet. The inability to fully understand and explain what has been done within the super-intelligence can turn an inherently benevolent system into malevolent. Recent research has revealed that the outputs of Deep Neural Networks (DNNs) can be easily corrupted by imperceptibly small input perturbations. As computations are brought nearer to the source of data creation, the attack surface of DNN has also been extended from the input data to the edge devices. Accordingly, due to the opportunities of ML-assisted security and the vulnerabilities of ML implementation, in this paper, we will survey the applications, vulnerabilities and fortification of ML from the perspective of hardware security. We will discuss the possible future research directions, and thereby, sharing a roadmap for the hardware security community in general. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Liu, Wenye Chang, Chip Hong Wang, Xueyang Liu, Chen Fung, Jason M. Mohammad Ebrahimabadi Karimi, Naghmeh Meng, Xingyu Basu, Kanad |
format |
Article |
author |
Liu, Wenye Chang, Chip Hong Wang, Xueyang Liu, Chen Fung, Jason M. Mohammad Ebrahimabadi Karimi, Naghmeh Meng, Xingyu Basu, Kanad |
author_sort |
Liu, Wenye |
title |
Two sides of the same coin : boons and banes of machine learning in hardware security |
title_short |
Two sides of the same coin : boons and banes of machine learning in hardware security |
title_full |
Two sides of the same coin : boons and banes of machine learning in hardware security |
title_fullStr |
Two sides of the same coin : boons and banes of machine learning in hardware security |
title_full_unstemmed |
Two sides of the same coin : boons and banes of machine learning in hardware security |
title_sort |
two sides of the same coin : boons and banes of machine learning in hardware security |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/155876 |
_version_ |
1728433428373700608 |