MUTEN: Mutant-Based Ensembles for Boosting Gradient-Based Adversarial Attack

Mutation testing (MT) for deep learning (DL) has gained huge attention in the past few years. However, how MT can really help DL is still unclear. In this paper, we introduce one promising direction for the usage of mutants. Specifically, since mutants can be seen as one kind of ensemble model and e...

Full description

Saved in:
Bibliographic Details
Published in:IEEE/ACM International Conference on Automated Software Engineering : [proceedings] pp. 1708 - 1712
Main Authors: Hu, Qiang, Guo, Yuejun, Cordy, Maxime, Papadakis, Mike, Traon, Yves Le
Format: Conference Proceeding
Language:English
Published: IEEE 11.09.2023
Subjects:
Boosting
Deep learning
Smoothing methods
Software engineering
Testing
Transform coding
ISSN:2643-1572
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Mutation testing (MT) for deep learning (DL) has gained huge attention in the past few years. However, how MT can really help DL is still unclear. In this paper, we introduce one promising direction for the usage of mutants. Specifically, since mutants can be seen as one kind of ensemble model and ensemble model can be used to boost the adversarial attack, we propose MUTEN, which applies the attack on mutants to improve the success rate of well-known attacks against gradient-masking models. Experimental results on MNIST, SVHN, and CIFAR-10 show that MUTEN can increase the success rate of four attacks by up to 45%. Furthermore, experiments on four defense approaches, bit-depth reduction, JPEG compression, Defensive distillation, and Label smoothing, demonstrate that MUTEN can break the defense models effectively by enhancing the attacks with the success rate of up to 96%.
AbstractList Mutation testing (MT) for deep learning (DL) has gained huge attention in the past few years. However, how MT can really help DL is still unclear. In this paper, we introduce one promising direction for the usage of mutants. Specifically, since mutants can be seen as one kind of ensemble model and ensemble model can be used to boost the adversarial attack, we propose MUTEN, which applies the attack on mutants to improve the success rate of well-known attacks against gradient-masking models. Experimental results on MNIST, SVHN, and CIFAR-10 show that MUTEN can increase the success rate of four attacks by up to 45%. Furthermore, experiments on four defense approaches, bit-depth reduction, JPEG compression, Defensive distillation, and Label smoothing, demonstrate that MUTEN can break the defense models effectively by enhancing the attacks with the success rate of up to 96%.
Author Traon, Yves Le
Guo, Yuejun
Cordy, Maxime
Papadakis, Mike
Hu, Qiang
Author_xml – sequence: 1
  givenname: Qiang
  surname: Hu
  fullname: Hu, Qiang
  organization: University of Luxembourg,Luxembourg
– sequence: 2
  givenname: Yuejun
  surname: Guo
  fullname: Guo, Yuejun
  organization: Luxembourg Institute of Science and Technology,Luxembourg
– sequence: 3
  givenname: Maxime
  surname: Cordy
  fullname: Cordy, Maxime
  organization: University of Luxembourg,Luxembourg
– sequence: 4
  givenname: Mike
  surname: Papadakis
  fullname: Papadakis, Mike
  organization: University of Luxembourg,Luxembourg
– sequence: 5
  givenname: Yves Le
  surname: Traon
  fullname: Traon, Yves Le
  organization: University of Luxembourg,Luxembourg
BookMark eNo9j81Kw0AURkdRsK19Al3MCyRO7vwk4y4tsQqpLmzX5WZyI9E2kZlR6NurKK4-DhwOfFN2NowDMXaViTTLhL0pnyttAGwKAmQqhFBwwuY2t4XUQoK1Rp2yCRglk0zncMGmIbwKob8hn7B6vd1Uj7d8_RFxiMkCA7W8GgIdmj0F3o2eL8YxxH544SuPbU__Vtl-kg_oe9zzMkZ0b5fsvMN9oPnfztj2rtos75P6afWwLOsEoVAxMY02DoxwLWGGRKCUNq2yoDXJ3GhtXdMVjpwD54pGo7LO2s50rcw7K42csevfbk9Eu3ffH9Afd5mAn8-5_ALyOU-6
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ASE56229.2023.00042
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISBN 9798350329964
EISSN 2643-1572
EndPage 1712
ExternalDocumentID 10298357
Genre orig-research
GroupedDBID 6IE
6IF
6IH
6IK
6IL
6IM
6IN
6J9
AAJGR
AAWTH
ABLEC
ACREN
ADYOE
ADZIZ
AFYQB
ALMA_UNASSIGNED_HOLDINGS
AMTXH
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
M43
OCL
RIE
RIL
ID FETCH-LOGICAL-a284t-6b56c260cdea1aee24456d49255e376559cbf8cecc2cc8b5a49c99f6fd37f9363
IEDL.DBID RIE
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001103357200139&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:32:41 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a284t-6b56c260cdea1aee24456d49255e376559cbf8cecc2cc8b5a49c99f6fd37f9363
PageCount 5
ParticipantIDs ieee_primary_10298357
PublicationCentury 2000
PublicationDate 2023-Sept.-11
PublicationDateYYYYMMDD 2023-09-11
PublicationDate_xml – month: 09
  year: 2023
  text: 2023-Sept.-11
  day: 11
PublicationDecade 2020
PublicationTitle IEEE/ACM International Conference on Automated Software Engineering : [proceedings]
PublicationTitleAbbrev ASE
PublicationYear 2023
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0051577
ssib057256115
Score 2.2652326
Snippet Mutation testing (MT) for deep learning (DL) has gained huge attention in the past few years. However, how MT can really help DL is still unclear. In this...
SourceID ieee
SourceType Publisher
StartPage 1708
SubjectTerms Boosting
Deep learning
Smoothing methods
Software engineering
Testing
Transform coding
Title MUTEN: Mutant-Based Ensembles for Boosting Gradient-Based Adversarial Attack
URI https://ieeexplore.ieee.org/document/10298357
WOSCitedRecordID wos001103357200139&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZoxcBUHkW85YE1EOfhB1uLAgy0qkQrdats5yIhoEFNyu_n7CZFDAxsURRZkc_2d5d8332EXCfAwsIRHLhNTJBIZgNT-K77ymitAU9A6c0mxHgs53M1acTqXgsDAJ58Bjfu0v_Lz0u7dp_KcIdHCjMG0SEdIfhGrNUunlQgeDO2zX0Rp4Vo2gyxUN0OXjKE-shpU6LY9-iMfhmqeDx56P3zTfZJ_0eZRydbzDkgO7A8JL3WmoE2O_WIPI9m02x8R0dr5xIcDBGrcpotK_gw71BRzFTpsCwrx3mmjytP-2qf8hbNlXYLkw7qWtu3Ppk9ZNP7p6AxTgg0ok0dcJNyi4WKzUEzDYAQnvLctSFMAQ8ULCKsKaTF6EXWSpPqRFmlCl7ksShUzONj0l2WSzghFMeLsN4OmTY2YVJIE8em4DqEUEuQ7JT03ewsPje9MRbtxJz9cf-c7LkAOMYFYxekW6_WcEl27Vf9Wq2ufES_AQWboDY
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LTsMwELSgIMGpPIp44wPXQJynza1FLUW0USVaiVtlOxsJAQlqUr6ftZsUceDALYoiK_Lant1kZoeQ6wCYmxmCQ6QD5QScaUdltuu-UFJKwBOQW7OJOEn4y4uY1GJ1q4UBAEs-gxtzaf_lp4Vemk9luMM9gRlDvEm2wiDw3JVcq1k-YYzwzdg6-0WkjuO60RBzxW33uY9g7xl1iufbLp3eL0sViyiD9j_fZY90frR5dLJGnX2yAfkBaTfmDLTeq4dkNJ5N-8kdHS-NT7DTQ7RKaT8v4UO9Q0kxV6W9oigN65k-LCzxq3nKmjSX0ixN2q0qqd86ZDboT--HTm2d4EjEm8qJVBhpLFV0CpJJAATxMEpNI8IQ8EjBMkKrjGuMn6c1V6EMhBYii7LUjzPhR_4RaeVFDseE4ngeVtwuk0oHjMdc-b7KIumCKzlwdkI6Znbmn6vuGPNmYk7_uH9FdobT8Wg-ekyezsiuCYbhXzB2TlrVYgkXZFt_Va_l4tJG9xuMO6N9
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=IEEE%2FACM+International+Conference+on+Automated+Software+Engineering+%3A+%5Bproceedings%5D&rft.atitle=MUTEN%3A+Mutant-Based+Ensembles+for+Boosting+Gradient-Based+Adversarial+Attack&rft.au=Hu%2C+Qiang&rft.au=Guo%2C+Yuejun&rft.au=Cordy%2C+Maxime&rft.au=Papadakis%2C+Mike&rft.date=2023-09-11&rft.pub=IEEE&rft.eissn=2643-1572&rft.spage=1708&rft.epage=1712&rft_id=info:doi/10.1109%2FASE56229.2023.00042&rft.externalDocID=10298357