On (in)security of edge-based machine learning against electromagnetic side-channels
Machine (deep) learning represents mainstream re- search and development direction. This success can be linked to the ever-increasing computational capabilities and vast amounts of available data, resulting in ever more sophisticated machine learning models. The design and training of such machine l...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/165224 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-165224 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1652242023-03-30T15:32:21Z On (in)security of edge-based machine learning against electromagnetic side-channels Bhasin, Shivam Jap, Dirmanto Picek, Stjepan 2022 IEEE International Symposium on Electromagnetic Compatibility & Signal/Power Integrity (EMCSI) Temasek Laboratories Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Engineering::Electrical and electronic engineering::Computer hardware, software and systems Side-Channel Analysis Machine Learning Machine (deep) learning represents mainstream re- search and development direction. This success can be linked to the ever-increasing computational capabilities and vast amounts of available data, resulting in ever more sophisticated machine learning models. The design and training of such machine learning models are challenging and expensive tasks, which incentivize companies to protect and keep it secret. Additionally, the wide applicability of machine learning results in diverse deployment scenarios. Many machine learning architectures are deployed on edge devices, such as sensors or actuators, making them susceptible to side-channel attacks. This work surveys the research works considering electromagnetic side-channel and edge-based machine learning models. After discussing state-of-the-art attacks and countermeasures, we propose several open problems to be investigated in future research. National Research Foundation (NRF) Submitted/Accepted version This research is supported in parts by the National Research Foundation, Singapore, under its National Cybersecurity Research & Development Programme/Cyber-Hardware Forensic & Assurance Evaluation R&D Programme (Award: NRF2018NCR-NCR009-0001). This work received funding in the framework of the NWA Cybersecurity Call with project name PROACT with project number NWA.1215.18.014, which is (partly) financed by the Netherlands Organisation for Scientific Research (NWO). Additionally, this work was supported in part by the Netherlands Organization for Scientific Research NWO project DISTANT (CS.019). 2023-03-27T08:03:21Z 2023-03-27T08:03:21Z 2022 Conference Paper Bhasin, S., Jap, D. & Picek, S. (2022). On (in)security of edge-based machine learning against electromagnetic side-channels. 2022 IEEE International Symposium on Electromagnetic Compatibility & Signal/Power Integrity (EMCSI), 262-267. https://dx.doi.org/10.1109/EMCSI39492.2022.9889639 https://hdl.handle.net/10356/165224 10.1109/EMCSI39492.2022.9889639 262 267 en NRF2018NCR-NCR009-0001 © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/EMCSI39492.2022.9889639. 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::Computing methodologies::Artificial intelligence Engineering::Electrical and electronic engineering::Computer hardware, software and systems Side-Channel Analysis Machine Learning |
spellingShingle |
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Engineering::Electrical and electronic engineering::Computer hardware, software and systems Side-Channel Analysis Machine Learning Bhasin, Shivam Jap, Dirmanto Picek, Stjepan On (in)security of edge-based machine learning against electromagnetic side-channels |
description |
Machine (deep) learning represents mainstream re- search and development direction. This success can be linked to the ever-increasing computational capabilities and vast amounts of available data, resulting in ever more sophisticated machine learning models. The design and training of such machine learning models are challenging and expensive tasks, which incentivize companies to protect and keep it secret.
Additionally, the wide applicability of machine learning results in diverse deployment scenarios. Many machine learning architectures are deployed on edge devices, such as sensors or actuators, making them susceptible to side-channel attacks. This work surveys the research works considering electromagnetic side-channel and edge-based machine learning models. After discussing state-of-the-art attacks and countermeasures, we propose several open problems to be investigated in future research. |
author2 |
2022 IEEE International Symposium on Electromagnetic Compatibility & Signal/Power Integrity (EMCSI) |
author_facet |
2022 IEEE International Symposium on Electromagnetic Compatibility & Signal/Power Integrity (EMCSI) Bhasin, Shivam Jap, Dirmanto Picek, Stjepan |
format |
Conference or Workshop Item |
author |
Bhasin, Shivam Jap, Dirmanto Picek, Stjepan |
author_sort |
Bhasin, Shivam |
title |
On (in)security of edge-based machine learning against electromagnetic side-channels |
title_short |
On (in)security of edge-based machine learning against electromagnetic side-channels |
title_full |
On (in)security of edge-based machine learning against electromagnetic side-channels |
title_fullStr |
On (in)security of edge-based machine learning against electromagnetic side-channels |
title_full_unstemmed |
On (in)security of edge-based machine learning against electromagnetic side-channels |
title_sort |
on (in)security of edge-based machine learning against electromagnetic side-channels |
publishDate |
2023 |
url |
https://hdl.handle.net/10356/165224 |
_version_ |
1762031104263454720 |