Harnessing Generative Modeling and Autoencoders Against Adversarial Threats in Autonomous Vehicles

The safety and security of Autonomous Vehicles (AVs) have been an active area of interest and study in recent years. To enable human behavior, Deep Learning (DL) and Machine Learning (ML) models are extensively used to make accurate decisions. However, the DL and ML models are susceptible to various...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on consumer electronics Vol. 70; no. 3; pp. 6216 - 6223
Main Authors:	Raja, Kathiroli, Theerthagiri, Sudhakar, Swaminathan, Sriram Venkataraman, Suresh, Sivassri, Raja, Gunasekaran
Format:	Journal Article
Language:	English
Published:	New York IEEE 01.08.2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Adversarial attacks Autonomous vehicles Closed box Decisions Deep learning generative denoising autoencoders Glass box Machine learning neural structured learning Noise Noise reduction Perturbation methods Training Vehicles
ISSN:	0098-3063, 1558-4127
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	The safety and security of Autonomous Vehicles (AVs) have been an active area of interest and study in recent years. To enable human behavior, Deep Learning (DL) and Machine Learning (ML) models are extensively used to make accurate decisions. However, the DL and ML models are susceptible to various attacks, like adversarial attacks, leading to miscalculated decisions. Existing solutions defend against adversarial attacks proactively or reactively. To improve the defense methodologies, we propose a novel hybrid Defense Strategy for Autonomous Vehicles against Adversarial Attacks (DSAA), incorporating both reactive and proactive measures with adversarial training with Neural Structured Learning (NSL) and a generative denoising autoencoder to remove the adversarial perturbations. In addition, a randomized channel that adds calculated noise to the model parameter is utilized to encounter white-box and black-box attacks. The experimental results demonstrate that the proposed DSAA effectively mitigates proactive and reactive attacks compared to other existing defense methods, showcasing its performance by achieving an average accuracy of 80.15%.
AbstractList	The safety and security of Autonomous Vehicles (AVs) have been an active area of interest and study in recent years. To enable human behavior, Deep Learning (DL) and Machine Learning (ML) models are extensively used to make accurate decisions. However, the DL and ML models are susceptible to various attacks, like adversarial attacks, leading to miscalculated decisions. Existing solutions defend against adversarial attacks proactively or reactively. To improve the defense methodologies, we propose a novel hybrid Defense Strategy for Autonomous Vehicles against Adversarial Attacks (DSAA), incorporating both reactive and proactive measures with adversarial training with Neural Structured Learning (NSL) and a generative denoising autoencoder to remove the adversarial perturbations. In addition, a randomized channel that adds calculated noise to the model parameter is utilized to encounter white-box and black-box attacks. The experimental results demonstrate that the proposed DSAA effectively mitigates proactive and reactive attacks compared to other existing defense methods, showcasing its performance by achieving an average accuracy of 80.15%.
Author	Raja, Kathiroli Swaminathan, Sriram Venkataraman Suresh, Sivassri Raja, Gunasekaran Theerthagiri, Sudhakar
Author_xml	– sequence: 1 givenname: Kathiroli orcidid: 0000-0003-0757-6750 surname: Raja fullname: Raja, Kathiroli email: kathiroli@mitindia.edu organization: Department of Computer Technology, NGNLab, Anna University, MIT Campus, Chennai, India – sequence: 2 givenname: Sudhakar orcidid: 0000-0002-1396-3223 surname: Theerthagiri fullname: Theerthagiri, Sudhakar email: tsudhakar105@gmail.com organization: Department of Computer Technology, NGNLab, Anna University, MIT Campus, Chennai, India – sequence: 3 givenname: Sriram Venkataraman surname: Swaminathan fullname: Swaminathan, Sriram Venkataraman email: g8sriram@gmail.com organization: Department of Computer Technology, NGNLab, Anna University, MIT Campus, Chennai, India – sequence: 4 givenname: Sivassri orcidid: 0009-0007-2386-0061 surname: Suresh fullname: Suresh, Sivassri email: sivassrisuresh@gmail.com organization: Department of Computer Technology, NGNLab, Anna University, MIT Campus, Chennai, India – sequence: 5 givenname: Gunasekaran orcidid: 0000-0002-2253-7648 surname: Raja fullname: Raja, Gunasekaran email: dr.r.gunasekaran@ieee.org organization: Department of Computer Technology, NGNLab, Anna University, MIT Campus, Chennai, India
BookMark	eNp9kDFPwzAQhS1UJNrCzsBgiTnFjp06GaOqtEhFLIU1cuxz6yq1i51W4t-T0A6IgeF0uqf33eneCA2cd4DQPSUTSknxtJ7NJylJ-YRxJjgtrtCQZlmecJqKARoSUuQJI1N2g0Yx7gihPEvzIaqXMjiI0boNXoCDIFt7AvzqNTS9Jp3G5bH14FQnhYjLjbQutrjUp26UwcoGr7cBZBuxdT9e5_f-GPEHbK1qIN6iayObCHeXPkbvz_P1bJms3hYvs3KVqLRI20RwwRRlTAlTkJpTrYSGnAqWKwNGGS54RlKoM1OTQgpJdZYBMUQLzQptDBujx_PeQ_CfR4httfPH4LqTFaOc95u6GqPp2aWCjzGAqZRtu6e9a4O0TUVJ1edZdXlWfZ7VJc8OJH_AQ7B7Gb7-Qx7OiAWAX_ZpyjJO2DcpL4QC
CODEN	ITCEDA
CitedBy_id	crossref_primary_10_3390_fi17080339
Cites_doi	10.1109/tsc.2024.3359608 10.1016/j.dcan.2020.04.007 10.1109/ACCESS.2019.2951526 10.1109/TCE.2023.3326384 10.1109/ACCESS.2024.3395976 10.1109/TIP.2021.3092582 10.1109/TII.2021.3113130 10.1109/IV51971.2022.9827222 10.1109/MSP.2012.2211477 10.1109/TCE.2023.3283704 10.1109/ACCESS.2019.2939352 10.1007/s11042-023-14702-9 10.1145/3133956.3134057 10.1109/TIP.2019.2940533 10.1109/OJVT.2023.3265363 10.1109/OJITS.2022.3142612 10.1109/CVPR.2016.350 10.1109/SP.2017.49 10.1007/978-3-030-01234-2_23 10.1109/TII.2020.3024643 10.1201/9781351251389-8 10.1109/TITS.2021.3130906 10.1109/ACCESS.2018.2807385 10.1109/TMC.2023.3290955 10.1109/TII.2020.3012166 10.1109/CVPR.2018.00957 10.1109/TCAD.2022.3166112 10.1109/TVT.2021.3127219 10.1109/IJCNN.2011.6033395 10.1016/j.enbenv.2020.05.002 10.1109/TII.2021.3071405
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID	97E RIA RIE AAYXX CITATION 7SP 8FD F28 FR3 L7M
DOI	10.1109/TCE.2024.3437419
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef Electronics & Communications Abstracts Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Engineering Research Database Technology Research Database Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering Electronics & Communications Abstracts
DatabaseTitleList	Engineering Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-4127
EndPage	6223
ExternalDocumentID	10_1109_TCE_2024_3437419 10623540
Genre	orig-research
GrantInformation_xml	– fundername: NGNLab, Department of Computer Technology, Anna University, MIT Campus, Chennai, India funderid: 10.13039/501100005968
GroupedDBID	-~X .DC 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABJNI ABQJQ ABVLG ACGFO ACIWK ACKIV ACNCT AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 IBMZZ ICLAB IFIPE IFJZH IPLJI JAVBF LAI MS~ O9- OCL P2P RIA RIE RNS TAE TN5 VH1 AAYXX CITATION 7SP 8FD F28 FR3 L7M
ID	FETCH-LOGICAL-c292t-7473c133c7f90b41dc7de81738cfefcf474502eb5fb09a7a1d55e0f0d7d39dff3
IEDL.DBID	RIE
ISICitedReferencesCount	1
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001378122400017&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0098-3063
IngestDate	Mon Jun 30 10:13:53 EDT 2025 Tue Nov 18 22:20:18 EST 2025 Sat Nov 29 01:45:45 EST 2025 Wed Aug 27 02:33:14 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	3
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c292t-7473c133c7f90b41dc7de81738cfefcf474502eb5fb09a7a1d55e0f0d7d39dff3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-2253-7648 0000-0002-1396-3223 0000-0003-0757-6750 0009-0007-2386-0061
PQID	3144173817
PQPubID	85469
PageCount	8
ParticipantIDs	crossref_primary_10_1109_TCE_2024_3437419 crossref_citationtrail_10_1109_TCE_2024_3437419 proquest_journals_3144173817 ieee_primary_10623540
PublicationCentury	2000
PublicationDate	2024-08-01
PublicationDateYYYYMMDD	2024-08-01
PublicationDate_xml	– month: 08 year: 2024 text: 2024-08-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on consumer electronics
PublicationTitleAbbrev	T-CE
PublicationYear	2024
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref35 ref12 ref34 ref15 ref37 ref14 ref31 ref30 ref11 ref33 ref10 ref32 Madry (ref27) 2017 ref2 ref1 ref17 ref19 ref18 Krizhevsky (ref22) 2009 ref23 ref26 ref25 Goodfellow (ref36) ref20 ref28 Goodfellow (ref24) 2014 ref29 ref8 ref7 Tramèr (ref16) ref9 ref4 ref3 ref6 ref5 Xiao (ref21) 2017
References_xml	– ident: ref35 doi: 10.1109/tsc.2024.3359608 – ident: ref6 doi: 10.1016/j.dcan.2020.04.007 – ident: ref11 doi: 10.1109/ACCESS.2019.2951526 – start-page: 1 volume-title: Proc. Int. Conf. Learn. Represent. ident: ref16 article-title: Ensemble adversarial training: Attacks and defenses – start-page: 1 volume-title: Proc. ICLR ident: ref36 article-title: Explaining and harnessing adversarial examples – ident: ref37 doi: 10.1109/TCE.2023.3326384 – ident: ref31 doi: 10.1109/ACCESS.2024.3395976 – ident: ref12 doi: 10.1109/TIP.2021.3092582 – ident: ref3 doi: 10.1109/TII.2021.3113130 – ident: ref14 doi: 10.1109/IV51971.2022.9827222 – ident: ref20 doi: 10.1109/MSP.2012.2211477 – ident: ref33 doi: 10.1109/TCE.2023.3283704 – ident: ref9 doi: 10.1109/ACCESS.2019.2939352 – ident: ref32 doi: 10.1007/s11042-023-14702-9 – ident: ref8 doi: 10.1145/3133956.3134057 – ident: ref10 doi: 10.1109/TIP.2019.2940533 – year: 2009 ident: ref22 article-title: Learning multiple layers of features from tiny images – ident: ref4 doi: 10.1109/OJVT.2023.3265363 – ident: ref29 doi: 10.1109/OJITS.2022.3142612 – year: 2014 ident: ref24 article-title: Explaining and harnessing adversarial examples publication-title: arXiv:1412.6572 – ident: ref23 doi: 10.1109/CVPR.2016.350 – ident: ref26 doi: 10.1109/SP.2017.49 – year: 2017 ident: ref27 article-title: Towards deep learning models resistant to adversarial attacks publication-title: arXiv:1706.06083 – ident: ref18 doi: 10.1007/978-3-030-01234-2_23 – ident: ref13 doi: 10.1109/TII.2020.3024643 – ident: ref15 doi: 10.1201/9781351251389-8 – year: 2017 ident: ref21 article-title: Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms publication-title: arXiv:1708.07747 – ident: ref17 doi: 10.1109/TITS.2021.3130906 – ident: ref7 doi: 10.1109/ACCESS.2018.2807385 – ident: ref34 doi: 10.1109/TMC.2023.3290955 – ident: ref5 doi: 10.1109/TII.2020.3012166 – ident: ref25 doi: 10.1109/CVPR.2018.00957 – ident: ref30 doi: 10.1109/TCAD.2022.3166112 – ident: ref2 doi: 10.1109/TVT.2021.3127219 – ident: ref28 doi: 10.1109/IJCNN.2011.6033395 – ident: ref1 doi: 10.1016/j.enbenv.2020.05.002 – ident: ref19 doi: 10.1109/TII.2021.3071405
SSID	ssj0014528
Score	2.4170198
Snippet	The safety and security of Autonomous Vehicles (AVs) have been an active area of interest and study in recent years. To enable human behavior, Deep Learning...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	6216
SubjectTerms	Adversarial attacks Autonomous vehicles Closed box Decisions Deep learning generative denoising autoencoders Glass box Machine learning neural structured learning Noise Noise reduction Perturbation methods Training Vehicles
Title	Harnessing Generative Modeling and Autoencoders Against Adversarial Threats in Autonomous Vehicles
URI	https://ieeexplore.ieee.org/document/10623540 https://www.proquest.com/docview/3144173817
Volume	70
WOSCitedRecordID	wos001378122400017&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
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-4127 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014528 issn: 0098-3063 databaseCode: RIE dateStart: 19750101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFG6EeNCDPzGiaHrw4mGwrR1dj4RAOBjiAQ23petaITGbYeDf73vdIBijibctaZtlX9v3vfa97xHyACZLRVxLD2yr8XiUGlhzNsVIgFgHKZDy1CUKP4npNJ7P5XOdrO5yYYwxLvjMdPHR3eVnhd7gURmscDDWQDEapCFEv0rW2l0Z8CiMtwKZwIPZ9k7Sl73ZcASeYMi7jDOwoPKbDXJFVX7sxM68jE__-WFn5KTmkXRQAX9ODkx-QY731AUvSTpRK9zI4IVW6tK4tVGsfoY56FTlGR1s1gVKWWI4Mx28qSWwReqKNJcKpyadLZBVlnSZu7Z5gUcF9NUsXDhdi7yMR7PhxKtLKng6lOHaA-eBaXBLtbDST3mQaZGZOBAs1tZYbbngkR-aNLKpL5VQQRZFxrd-JjImM2vZFWnmRW6uCUXFX3BvlGIBA1YAo1gpAXUeaKX7xm-T3vYnJ7rWG8eyF--J8zt8mQAsCcKS1LC0yeOux0eltfFH2xbCsNeuQqBNOlsgk3o1lglDr1GgFuHNL91uyRGOXkX2dUhzvdqYO3KoP9fLcnXvJtoXYg_Qew
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB58gXrwLa7PHLx4qKZNapvjIi4rrouHVbyVNE3cBenKPvz9zqTdRREFby0kbemXZL5JZr4BOEeTpWNpVIC21QYyzi3OOZdTJEBqwhxJee4ThTtJt5u-vKjHOlnd58JYa33wmb2kS3-WXwzNlLbKcIajsUaKsQjLsZQRr9K15ocGMo7SmUQmMmExO5Xk6qp3c4u-YCQvhRRoQ9U3K-TLqvxYi72BaW3-89O2YKNmkqxZQb8NC7bcgfUv-oK7kLf1iJYyvGGVvjQtbozqn1EWOtNlwZrTyZDELCmgmTVf9QD5IvNlmseaBifr9YlXjtmg9G3LIW0WsGfb9wF1e_DUuu3dtIO6qEJgIhVNAnQfhEHH1CRO8VyGhUkKm4aJSI2zzjiZyJhHNo9dzpVOdFjEseWOF0khVOGc2IelcljaA2Ck-YsOjtYiFMgL8ClOKcRdhkaba8sbcDX7yZmpFcep8MVb5j0PrjKEJSNYshqWBlzMe7xXaht_tN0jGL60qxBowPEMyKyej-NMkN-YkBrh4S_dzmC13XvoZJ277v0RrNGbqji_Y1iajKb2BFbMx2QwHp36QfcJYpHTwg
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%3Ajournal&rft.genre=article&rft.atitle=Harnessing+Generative+Modeling+and+Autoencoders+Against+Adversarial+Threats+in+Autonomous+Vehicles&rft.jtitle=IEEE+transactions+on+consumer+electronics&rft.au=Raja%2C+Kathiroli&rft.au=Theerthagiri%2C+Sudhakar&rft.au=Swaminathan%2C+Sriram+Venkataraman&rft.au=Suresh%2C+Sivassri&rft.date=2024-08-01&rft.issn=0098-3063&rft.eissn=1558-4127&rft.volume=70&rft.issue=3&rft.spage=6216&rft.epage=6223&rft_id=info:doi/10.1109%2FTCE.2024.3437419&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TCE_2024_3437419
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0098-3063&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0098-3063&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0098-3063&client=summon