Exploiting Power Side-Channel Vulnerabilities in XGBoost Accelerator

XGBoost (eXtreme Gradient Boosting), a widelyused decision tree algorithm, plays a crucial role in applications such as ransomware and fraud detection. While its performance is well-established, its security against model extraction on hardware platforms like Field Programmable Gate Arrays (FPGAs) h...

Full description

Saved in:
Bibliographic Details
Published in:2025 62nd ACM/IEEE Design Automation Conference (DAC) pp. 1 - 7
Main Authors: Xiao, Yimeng, Gajjar, Archit, Aysu, Aydin, Franzon, Paul
Format: Conference Proceeding
Language:English
Published: IEEE 22.06.2025
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract XGBoost (eXtreme Gradient Boosting), a widelyused decision tree algorithm, plays a crucial role in applications such as ransomware and fraud detection. While its performance is well-established, its security against model extraction on hardware platforms like Field Programmable Gate Arrays (FPGAs) has not been fully explored. In this paper, we demonstrate a significant vulnerability where sensitive model data can be leaked from an XGBoost implementation through side-channel attacks (SCAs). By analyzing variations in power consumption, we show how an attacker can infer node features within the XGBoost model, leading to the extraction of critical data. We conduct an experiment using the XGBoost accelerator FAXID on the Sakura-X platform, demonstrating a method to deduce model decisions by monitoring power consumptions. The results show that on average 367k tests are sufficient to leak sensitive values. Our findings underscore the need for improved hardware and algorithmic protections to safeguard machine learning models from these types of attacks.
AbstractList XGBoost (eXtreme Gradient Boosting), a widelyused decision tree algorithm, plays a crucial role in applications such as ransomware and fraud detection. While its performance is well-established, its security against model extraction on hardware platforms like Field Programmable Gate Arrays (FPGAs) has not been fully explored. In this paper, we demonstrate a significant vulnerability where sensitive model data can be leaked from an XGBoost implementation through side-channel attacks (SCAs). By analyzing variations in power consumption, we show how an attacker can infer node features within the XGBoost model, leading to the extraction of critical data. We conduct an experiment using the XGBoost accelerator FAXID on the Sakura-X platform, demonstrating a method to deduce model decisions by monitoring power consumptions. The results show that on average 367k tests are sufficient to leak sensitive values. Our findings underscore the need for improved hardware and algorithmic protections to safeguard machine learning models from these types of attacks.
Author Gajjar, Archit
Aysu, Aydin
Franzon, Paul
Xiao, Yimeng
Author_xml – sequence: 1
  givenname: Yimeng
  surname: Xiao
  fullname: Xiao, Yimeng
  email: yxiao32@ncsu.edu
  organization: North Carolina State University,Dept. Electrical and Computer Engineering,Raleigh,NC,USA
– sequence: 2
  givenname: Archit
  surname: Gajjar
  fullname: Gajjar, Archit
  email: amgajjar@ncsu.edu
  organization: North Carolina State University,Dept. Electrical and Computer Engineering,Raleigh,NC,USA
– sequence: 3
  givenname: Aydin
  surname: Aysu
  fullname: Aysu, Aydin
  email: aaysu@ncsu.edu
  organization: North Carolina State University,Dept. Electrical and Computer Engineering,Raleigh,NC,USA
– sequence: 4
  givenname: Paul
  surname: Franzon
  fullname: Franzon, Paul
  email: paulf@ncsu.edu
  organization: North Carolina State University,Dept. Electrical and Computer Engineering,Raleigh,NC,USA
BookMark eNo1j99KwzAYxSPohc69gUheoDNfkzTNZe3mFAYb-AfvRtJ80UBMRltR396KenU453c4cM7IccoJCbkEtgBg-mrZtBWvhV6UrJRTBJwzUR-RuVa65hwk-_GnZLn6PMQcxpBe6C5_YE_vg8OifTUpYaRP7zFhb2yIUwUHGhJ9Xl_nPIy06TqMExtzf05OvIkDzv90Rh5vVg_tbbHZru_aZlMYUHosFGIlAK2ufaeVsxakd6Wy2jmB3njFuauNBSErLZnyotSKGWUUgKws03xGLn53AyLuD314M_3X_v8c_waMp0lG
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/DAC63849.2025.11133048
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 11133048
Genre orig-research
GrantInformation_xml – fundername: National Science Foundation
  funderid: 10.13039/100000001
GroupedDBID 6IE
6IH
CBEJK
RIE
RIO
ID FETCH-LOGICAL-a179t-7ee641eb98fc97dbb15fd27b9dd4efaf733d8ab14569507f42970a7a71156b093
IEDL.DBID RIE
IngestDate Wed Oct 01 07:05:15 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a179t-7ee641eb98fc97dbb15fd27b9dd4efaf733d8ab14569507f42970a7a71156b093
PageCount 7
ParticipantIDs ieee_primary_11133048
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 2.2951725
Snippet XGBoost (eXtreme Gradient Boosting), a widelyused decision tree algorithm, plays a crucial role in applications such as ransomware and fraud detection. While...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Data models
Decision trees
Feature extraction
Field programmable gate arrays
FPGAs
hardware security
HLS
Machine learning algorithms
Monitoring
Power demand
Protection
Ransomware
side-channel attack
Side-channel attacks
XGBoost
Title Exploiting Power Side-Channel Vulnerabilities in XGBoost Accelerator
URI https://ieeexplore.ieee.org/document/11133048
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwFLSgYmACRBHf8sDqNkndvHgsLYUBVZX4ULfKH89SpCpBbcrv59ltQQwMbFEUJYod--7iOz_G7pQjGg5GC8htJiT4XBhJYsUS1TbKEKCbWLXkGSaTYjZT021YPWZhEDGaz7ATDuNavqvtOvwq64ay6CS_i322D5Bvwlrb1G-aqO5oMKSvSYb4Sdbv7C7-VTYlosb46J_PO2btn_wdn34jywnbw-qUjaJdrgw2ZT4Ntc34S-lQhHhAhQv-vl6EDaSj15XULy8rPnu8r-tVwwfWErjE9fQ2exs_vA6fxLYGgtA0VBoBiLlM0ajCWwXOmLTvXQZGOSfRaw-9niu0SYkHKaJ2nuAFEg0aiOnlJlG9M9aq6grPGTfOJzSZabqhkjIxpHQckECy2Aep0-KCtUMTzD8221zMd29_-cf5K3YYGjr4prLsmrWa5Rpv2IH9bMrV8jZ2zhfucJG1
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwGP3QKehJxYm_zcFrtrZLm-Y4N-fEOQZO2W3kV6EwWtk6_36_xE7x4MFbKaWlSZP3vua9PIBbYZCGcyUpT3REGc8SqhgWKxqpthIKAV351JIRH4_T2UxMarO698JYa734zLbcoV_LN6Veu19lbReLjuV3ug07LjqrtmvVvt8wEO1-t4ffE3MGlChubS7_FZzicWNw8M8nHkLzx4FHJt_YcgRbtjiGvhfM5U6oTCYu3Yy85MZSZxAo7IK8rRduC2mvdsX6l-QFmT3cleWqIl2tEV78inoTXgf3096Q1ikIVOJgqSi3NmGhVSLNtOBGqTDOTMSVMIbZTGa80zGpVCEyIYHkLkOA4YHkkiPXS1QgOifQKMrCngJRJgtwOpN4Q8FYoLDWMRxLJG1jzmSYnkHTNcH8_Wuji_nm7c__OH8De8Pp82g-ehw_XcC-a3SnooqiS2hUy7W9gl39UeWr5bXvqE-2hJT-
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=Exploiting+Power+Side-Channel+Vulnerabilities+in+XGBoost+Accelerator&rft.au=Xiao%2C+Yimeng&rft.au=Gajjar%2C+Archit&rft.au=Aysu%2C+Aydin&rft.au=Franzon%2C+Paul&rft.date=2025-06-22&rft.pub=IEEE&rft.spage=1&rft.epage=7&rft_id=info:doi/10.1109%2FDAC63849.2025.11133048&rft.externalDocID=11133048