Security of Approximate Neural Networks against Power Side-channel Attacks

Emerging low-energy computing technologies, in particular approximate computing, are becoming increasingly relevant in key applications. A significant use case for these technologies is reduced energy consumption in Artificial Neural Networks (ANNs), an increasingly pressing concern with the rapid g...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2025 62nd ACM/IEEE Design Automation Conference (DAC) s. 1 - 7
Hlavní autoři: Japa, Aditya, Miskelly, Jack, O'Neill, Maire, Gu, Chongyan
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 22.06.2025
Témata:
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Emerging low-energy computing technologies, in particular approximate computing, are becoming increasingly relevant in key applications. A significant use case for these technologies is reduced energy consumption in Artificial Neural Networks (ANNs), an increasingly pressing concern with the rapid growth of AI deployments. It is essential we understand the security implications of approximate computing in an ANN context before this practice becomes commonplace. In this work, we examine the test case of approximate ANN processing elements (PE) in terms of information leakage via the power side channel. We perform a weight extraction correlation Power Analysis (CPA) attack under three approximation scenarios: overclocking, voltage scaling, and circuit level bitwise approximation. We demonstrate that as the degree of approximation increases the Signal to Noise Ratio (SNR) of power traces rapidly degrades. We show that the Measurement to Disclosure (MTD) increases for all approximate techniques. An MTD of 48 under precise computing is increased to at minimum 200 (bitwise approximate circuit at \mathbf{2 5 \%} approximation), and under some approximation scenarios \gt1024. i.e. an increase in attack difficulty of at least x4 and potentially over x20. A relative Security-Power-Delay (SPD) analysis reveals that, in addition to the across the board improvement vs precise computing, voltage and clock scaling both significantly outperform approximate circuits with voltage scaling as the highest performing technique.
AbstractList Emerging low-energy computing technologies, in particular approximate computing, are becoming increasingly relevant in key applications. A significant use case for these technologies is reduced energy consumption in Artificial Neural Networks (ANNs), an increasingly pressing concern with the rapid growth of AI deployments. It is essential we understand the security implications of approximate computing in an ANN context before this practice becomes commonplace. In this work, we examine the test case of approximate ANN processing elements (PE) in terms of information leakage via the power side channel. We perform a weight extraction correlation Power Analysis (CPA) attack under three approximation scenarios: overclocking, voltage scaling, and circuit level bitwise approximation. We demonstrate that as the degree of approximation increases the Signal to Noise Ratio (SNR) of power traces rapidly degrades. We show that the Measurement to Disclosure (MTD) increases for all approximate techniques. An MTD of 48 under precise computing is increased to at minimum 200 (bitwise approximate circuit at \mathbf{2 5 \%} approximation), and under some approximation scenarios \gt1024. i.e. an increase in attack difficulty of at least x4 and potentially over x20. A relative Security-Power-Delay (SPD) analysis reveals that, in addition to the across the board improvement vs precise computing, voltage and clock scaling both significantly outperform approximate circuits with voltage scaling as the highest performing technique.
Author Miskelly, Jack
Gu, Chongyan
Japa, Aditya
O'Neill, Maire
Author_xml – sequence: 1
  givenname: Aditya
  surname: Japa
  fullname: Japa, Aditya
  email: a.japa@ulster.ac.uk
  organization: Ulster University,School of Computing, Engineering and Intelligent Systems,Derry,U.K
– sequence: 2
  givenname: Jack
  surname: Miskelly
  fullname: Miskelly, Jack
  email: c.gu@qub.ac.uk
  organization: Queen's University Belfast,Centre for Secure Information Technologies,Belfast,U.K
– sequence: 3
  givenname: Maire
  surname: O'Neill
  fullname: O'Neill, Maire
  organization: Queen's University Belfast,Centre for Secure Information Technologies,Belfast,U.K
– sequence: 4
  givenname: Chongyan
  surname: Gu
  fullname: Gu, Chongyan
  organization: Queen's University Belfast,Centre for Secure Information Technologies,Belfast,U.K
BookMark eNo1j8tOwzAURI0ECyj9A4T8Ayl-xEm8jMJbVYtUWFfX9jVEDU7kuCr9e4KA2RxpFkczF-Q09AEJueZswTnTN7d1U8gq1wvBhJoqLn9yQua61JWUXDHJ8uqcPG_Q7mObjrT3tB6G2H-1n5CQrnAfoZuQDn3cjRTeoQ1joi_9ASPdtA4z-wEhYEfrlMDuxkty5qEbcf7HGXm7v3ttHrPl-uGpqZcZ8FKnDFBwywtt0VTOgXA5SOsYU2hLBKaUycFxk4tSamW9AWY9SlYIXyojjJYzcvXrbRFxO8Rpbzxu_y_Kb92ZTII
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/DAC63849.2025.11133333
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331503048
EndPage 7
ExternalDocumentID 11133333
Genre orig-research
GroupedDBID 6IE
6IH
CBEJK
RIE
RIO
ID FETCH-LOGICAL-a179t-ae21c169ceb8dda2d4a3cd005ec7ea055b4ad1b427395cfba0cfe3062f75b2b93
IEDL.DBID RIE
IngestDate Wed Oct 01 07:05:15 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a179t-ae21c169ceb8dda2d4a3cd005ec7ea055b4ad1b427395cfba0cfe3062f75b2b93
PageCount 7
ParticipantIDs ieee_primary_11133333
PublicationCentury 2000
PublicationDate 2025-June-22
PublicationDateYYYYMMDD 2025-06-22
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-June-22
  day: 22
PublicationDecade 2020
PublicationTitle 2025 62nd ACM/IEEE Design Automation Conference (DAC)
PublicationTitleAbbrev DAC
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
Score 2.2953122
Snippet Emerging low-energy computing technologies, in particular approximate computing, are becoming increasingly relevant in key applications. A significant use case...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Approximate computing
Artificial intelligence
Artificial neural networks
Clocks
Information leakage
Neural network hardware
Power Side-channel attacks
Pressing
Security
Side-channel attacks
Signal to noise ratio
Timing
Title Security of Approximate Neural Networks against Power Side-channel Attacks
URI https://ieeexplore.ieee.org/document/11133333
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NSwMxEA22ePCkYsVvcvC6bTabbXaPpVpEpBSq0luZJLNSKFvpbsWfbybdKh48mEMSQiAwSUheMm8eY7cqgUwUDv3NzUKkVOIiEDFl2sOJzPZt0Dp8fdLjcTab5ZOGrB64MIgYnM-wS9Xwl-9WdkNPZT2SRafUYi2t-1uyVsP6jUXeuxsM_WpSRD-RaXfX-ZdsSjg1Rof_HO-IdX74d3zyfbIcsz0sT9jjtJGa46uCDygU-OfCXzeRU3wNWPoiOHRXHN482q9qPiEBND5deBMRvbfEJR_UNXHqO-xldP88fIgaJYQI_IapI0AZ27ifWzSZcyCdgsQ6v4HQagSRpkaBi42S9O1mCwPCFujBgCx0aqTJk1PWLlclnjFemNTmTqQCLXpojACYCyycTbSHXoDnrEOGmL9vg13Mdza4-KP9kh2Qucl7Ssor1q7XG7xm-_ajXlTrmzBFXzQ8leU
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA46BT2pOPG3OXjtlqbp2h7HdEydY7Apu43X5EUGo5WtE_9887pO8eDBHJIQAoGXhORL3vc-xm5VALGwBt3NTYOnVGA8ED5lkYMTsW7pUuvwtR8NBvFkkgwrsnrJhUHE0vkMG1Qt__JNrlf0VNYkWXRK22wnVEqKNV2r4v36ImnetTtuPSkioMiwsen-SzilPDe6B_8c8ZDVfxh4fPh9thyxLcyO2eOoEpvjueVtCgb-OXMXTuQUYQPmrihdupcc3hzeXxZ8SBJofDRzRiKCb4Zz3i4KYtXX2Uv3ftzpeZUWggduyxQeoPS130o0prExII2CQBu3hVBHCCIMUwXGT5WkjzdtUxDaooMD0kZhKtMkOGG1LM_wlHGbhjoxIhSo0YFjBMBEoDU6iBz4AjxjdTLE9H0d7mK6scH5H-03bK83fu5P-w-Dpwu2T6YnXyopL1mtWKzwiu3qj2K2XFyX0_UFLcuZLA
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2025+62nd+ACM%2FIEEE+Design+Automation+Conference+%28DAC%29&rft.atitle=Security+of+Approximate+Neural+Networks+against+Power+Side-channel+Attacks&rft.au=Japa%2C+Aditya&rft.au=Miskelly%2C+Jack&rft.au=O%27Neill%2C+Maire&rft.au=Gu%2C+Chongyan&rft.date=2025-06-22&rft.pub=IEEE&rft.spage=1&rft.epage=7&rft_id=info:doi/10.1109%2FDAC63849.2025.11133333&rft.externalDocID=11133333