QoS Prediction and Adversarial Attack Protection for Distributed Services Under DLaaS

Deep-Learning-as-a-service (DLaaS) has received increasing attention due to its novelty as a diagram for deploying deep learning techniques. However, DLaaS faces performance and security issues that urgently need to be addressed. Given the limited computation resources and concern of benefits, Quali...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on computers Jg. 73; H. 3; S. 669 - 682
Hauptverfasser:	Liang, Wei, Li, Yuhui, Xu, Jianlong, Qin, Zheng, Zhang, Dafang, Li, Kuan-Ching
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York IEEE 01.03.2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Adversarial attacks Computational modeling Deep learning dlaas graph neural network Internet of Things Neural networks Performance evaluation Predictive models probability forecast qos prediction Quality of service Recommender systems Security Uncertainty
ISSN:	0018-9340, 1557-9956
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Deep-Learning-as-a-service (DLaaS) has received increasing attention due to its novelty as a diagram for deploying deep learning techniques. However, DLaaS faces performance and security issues that urgently need to be addressed. Given the limited computation resources and concern of benefits, Quality-of-Service (QoS) metrics should be revised to optimize the performance and reliability of distributed DLaaS systems. New users and services dynamically and continuously join and leave such a system, resulting in cold start issues, and additionally, the increasing demand for robust network connections requires the model to evaluate the uncertainty. To address such performance problems, we propose in this article a deep learning-based model called embedding enhanced probability neural network, in which information is extracted from inside the graph structure and then estimated the mean and variance values for the prediction distribution. The adversarial attack is a severe threat to model security under DLaaS. Due to such, the service recommender system's vulnerability is tackled, and adversarial training with uncertainty-aware loss to protect the model in noisy and adversarial environments is investigated and proposed. Extensive experiments on a large-scale real-world QoS dataset are conducted, and comprehensive analysis verifies the robustness and effectiveness of the proposed model.
AbstractList	Deep-Learning-as-a-service (DLaaS) has received increasing attention due to its novelty as a diagram for deploying deep learning techniques. However, DLaaS faces performance and security issues that urgently need to be addressed. Given the limited computation resources and concern of benefits, Quality-of-Service (QoS) metrics should be revised to optimize the performance and reliability of distributed DLaaS systems. New users and services dynamically and continuously join and leave such a system, resulting in cold start issues, and additionally, the increasing demand for robust network connections requires the model to evaluate the uncertainty. To address such performance problems, we propose in this article a deep learning-based model called embedding enhanced probability neural network, in which information is extracted from inside the graph structure and then estimated the mean and variance values for the prediction distribution. The adversarial attack is a severe threat to model security under DLaaS. Due to such, the service recommender system's vulnerability is tackled, and adversarial training with uncertainty-aware loss to protect the model in noisy and adversarial environments is investigated and proposed. Extensive experiments on a large-scale real-world QoS dataset are conducted, and comprehensive analysis verifies the robustness and effectiveness of the proposed model.
Author	Li, Kuan-Ching Li, Yuhui Xu, Jianlong Zhang, Dafang Liang, Wei Qin, Zheng
Author_xml	– sequence: 1 givenname: Wei orcidid: 0000-0002-5074-1363 surname: Liang fullname: Liang, Wei email: weiliang99@hnu.edu.cn organization: College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China – sequence: 2 givenname: Yuhui surname: Li fullname: Li, Yuhui email: 17yhli3@stu.edu.cn organization: College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China – sequence: 3 givenname: Jianlong orcidid: 0000-0003-2826-9282 surname: Xu fullname: Xu, Jianlong email: xujianlong@stu.edu.cn organization: Computer Science Department, Colleage of Engineering, Shantou University, Shantou, Guangdong, China – sequence: 4 givenname: Zheng orcidid: 0000-0003-0877-3887 surname: Qin fullname: Qin, Zheng email: zqin@hnu.edu.cn organization: College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China – sequence: 5 givenname: Dafang surname: Zhang fullname: Zhang, Dafang email: dfzhang@hnu.edu.cn organization: College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China – sequence: 6 givenname: Kuan-Ching orcidid: 0000-0003-1381-4364 surname: Li fullname: Li, Kuan-Ching email: kuancli@pu.edu.tw organization: Department of Computer Science and Information Engineering (CSIE), Providence University, Shalu, Taichung, Taiwan
BookMark	eNp9kEtPAjEURhujiYCu3biYxPXAbUun7ZLgMyFRA6ybTttJijjFtpD47x0yLIwLV3dxz7mPb4jO29A6hG4wjDEGOVnNxwQIHlPgnFNxhgaYMV5KyapzNADAopR0CpdomNIGACoCcoDW72FZvEVnvck-tIVubTGzBxeTjl5vi1nO2nx0RMiuJ5oQi3ufcvT1PjtbLF08eONSsW6t61oLrZdX6KLR2-SuT3WE1o8Pq_lzuXh9epnPFqUhEnJJrNVG0spiXoPVjHBZYWa4EBKsEFQ6CayBqakbzgghtOYcE9r1mKw1qegI3fVzdzF87V3KahP2se1WKiLJFGhFBe0o1lMmhpSia5TxWR-fyVH7rcKgjgmq1VwdE1SnBDtv8sfbRf-p4_c_xm1veOfcLxpLJrprfgCG_Xu8
CODEN	ITCOB4
CitedBy_id	crossref_primary_10_1007_s11227_024_06160_3 crossref_primary_10_1109_TNSE_2025_3550566 crossref_primary_10_1109_TDSC_2024_3519197 crossref_primary_10_1016_j_future_2024_04_028 crossref_primary_10_1109_TR_2022_3190932 crossref_primary_10_1080_09540091_2024_2312121 crossref_primary_10_1007_s10586_021_03399_w crossref_primary_10_1007_s42979_025_03879_5 crossref_primary_10_1109_JIOT_2025_3578198 crossref_primary_10_1109_TCC_2024_3522993 crossref_primary_10_3390_s23218744 crossref_primary_10_1016_j_inffus_2025_103297 crossref_primary_10_1109_TITS_2022_3156266 crossref_primary_10_1016_j_dcan_2025_03_004 crossref_primary_10_1109_TNSM_2025_3570464 crossref_primary_10_1016_j_jii_2025_100946 crossref_primary_10_1109_TSC_2025_3559613 crossref_primary_10_1109_JIOT_2024_3379363 crossref_primary_10_1177_17298806241312786 crossref_primary_10_1007_s11227_025_07323_6 crossref_primary_10_1145_3676164 crossref_primary_10_1145_3717069 crossref_primary_10_1002_dac_5395 crossref_primary_10_1109_TII_2021_3129631
Cites_doi	10.1109/TR.2015.2464075 10.1109/TSC.2012.34 10.1109/TSC.2011.59 10.1016/j.future.2019.05.024 10.1016/j.knosys.2017.10.001 10.1109/ICWS.2014.51 10.1109/JIOT.2020.3004498 10.1016/j.ejor.2007.07.015 10.1109/TSC.2010.52 10.1109/ICWS.2018.00012 10.1109/ICWS.2015.60 10.1109/SOCA.2014.11 10.24963/ijcai.2017/239 10.1109/ICWS.2010.27 10.1109/TII.2019.2903342 10.1109/ICWS.2012.61 10.1016/j.future.2017.06.020 10.1145/2988450.2988454 10.1109/jiot.2020.3014845 10.1109/SCC.2014.23 10.1145/3391297 10.1145/2430545.2430548 10.1109/jiot.2021.3053842 10.1109/jiot.2020.3048038 10.1080/09540091.2021.1889975 10.1002/cpe.3639 10.1007/978-3-030-60239-0_19 10.1109/tii.2020.3047843 10.1109/BigDataSecurity-HPSC-IDS49724.2020.00027 10.1109/TII.2020.3008010 10.1109/tsc.2018.2859986 10.1145/3038912.3052569 10.1109/JIOT.2020.2974281 10.1109/TSC.2012.31 10.1109/ICWS.2007.140 10.1109/MIC.2003.1167344 10.1145/3426968 10.1109/tsc.2019.2891517 10.1109/TITS.2019.2900481 10.1109/tetc.2020.2993032
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 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TC.2021.3077738
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology 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 Computer Science
EISSN	1557-9956
EndPage	682
ExternalDocumentID	10_1109_TC_2021_3077738 10195840
Genre	orig-research
GrantInformation_xml	– fundername: Fundamental Research Funds for the Central Universities grantid: 531118010527 funderid: 10.13039/501100012226 – fundername: National Natural Science Foundation of China grantid: 61702318; 62072170 funderid: 10.13039/501100001809 – fundername: 2020 Li Ka Shing Foundation Cross-Disciplinary Research grantid: 2020LKSFG08D – fundername: 2019 Guangdong Province Special Fund for Science and Technology grantid: 2019ST043
GroupedDBID	--Z -DZ -~X .55 .DC 0R~ 29I 3EH 3O- 4.4 5GY 5VS 6IK 85S 97E AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACIWK ACNCT AENEX AETEA AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD HZ~ H~9 IAAWW IBMZZ ICLAB IEDLZ IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ MVM O9- OCL P2P PQQKQ RIA RIE RNI RNS RXW RZB TAE TN5 TWZ UHB UKR UPT VH1 X7M XJT XOL XZL YXB YYQ YZZ ZCG AAYXX ABUFD CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c290t-2ddac936d17b0da5279615c78890d8839e905f04cbf752223b771230d859ba263
IEDL.DBID	RIE
ISICitedReferencesCount	162
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001167590600015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0018-9340
IngestDate	Sun Nov 09 06:14:46 EST 2025 Sat Nov 29 01:35:45 EST 2025 Tue Nov 18 22:18:33 EST 2025 Wed Aug 27 02:12:03 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-c290t-2ddac936d17b0da5279615c78890d8839e905f04cbf752223b771230d859ba263
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-5074-1363 0000-0003-2826-9282 0000-0003-0877-3887 0000-0003-1381-4364
PQID	2924036383
PQPubID	85452
PageCount	14
ParticipantIDs	proquest_journals_2924036383 ieee_primary_10195840 crossref_citationtrail_10_1109_TC_2021_3077738 crossref_primary_10_1109_TC_2021_3077738
PublicationCentury	2000
PublicationDate	2024-03-01
PublicationDateYYYYMMDD	2024-03-01
PublicationDate_xml	– month: 03 year: 2024 text: 2024-03-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on computers
PublicationTitleAbbrev	TC
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 ref36 ref31 ref30 ref11 ref33 Glorot (ref41) ref10 ref32 ref2 ref1 ref17 ref16 ref38 ref19 ref18 Kendall (ref42) Xu (ref27) 2016; 53 ref24 ref46 ref23 ref45 ref26 ref25 ref47 ref20 Kipf (ref39) 2017 ref22 ref44 ref21 ref28 Kingma (ref48) ref29 ref8 ref7 ref9 ref4 Vaswani (ref40) 2017 ref3 Liu (ref14) 2020; 541 ref6 ref5 Miyato (ref43) 2017
References_xml	– ident: ref29 doi: 10.1109/TR.2015.2464075 – ident: ref44 doi: 10.1109/TSC.2012.34 – year: 2017 ident: ref43 article-title: Adversarial training methods for semi-supervised text classification – ident: ref30 doi: 10.1109/TSC.2011.59 – ident: ref35 doi: 10.1016/j.future.2019.05.024 – ident: ref37 doi: 10.1016/j.knosys.2017.10.001 – ident: ref25 doi: 10.1109/ICWS.2014.51 – ident: ref10 doi: 10.1109/JIOT.2020.3004498 – ident: ref8 doi: 10.1016/j.ejor.2007.07.015 – ident: ref18 doi: 10.1109/TSC.2010.52 – ident: ref34 doi: 10.1109/ICWS.2018.00012 – ident: ref20 doi: 10.1109/ICWS.2015.60 – ident: ref31 doi: 10.1109/SOCA.2014.11 – ident: ref46 doi: 10.24963/ijcai.2017/239 – ident: ref22 doi: 10.1109/ICWS.2010.27 – year: 2017 ident: ref39 article-title: Semi-supervised classification with graph convolutional networks – ident: ref12 doi: 10.1109/TII.2019.2903342 – ident: ref23 doi: 10.1109/ICWS.2012.61 – start-page: 5574 volume-title: Proc. Annu. Conf. Neural Inf. Process. Syst. ident: ref42 article-title: What uncertainties do we need in Bayesian deep learning for computer vision? – ident: ref28 doi: 10.1016/j.future.2017.06.020 – ident: ref38 doi: 10.1145/2988450.2988454 – ident: ref6 doi: 10.1109/jiot.2020.3014845 – ident: ref26 doi: 10.1109/SCC.2014.23 – volume: 541 start-page: 297 volume-title: Inf. Sci. year: 2020 ident: ref14 article-title: Attention-based bidirectional GRU networks for efficient HTTPS traffic classification – ident: ref1 doi: 10.1145/3391297 – ident: ref24 doi: 10.1145/2430545.2430548 – ident: ref7 doi: 10.1109/jiot.2021.3053842 – ident: ref11 doi: 10.1109/jiot.2020.3048038 – start-page: 1 volume-title: Proc. 3rd Int. Conf. Learn. Representations ident: ref48 article-title: Adam: A method for stochastic optimization – ident: ref36 doi: 10.1080/09540091.2021.1889975 – ident: ref21 doi: 10.1002/cpe.3639 – ident: ref15 doi: 10.1007/978-3-030-60239-0_19 – ident: ref4 doi: 10.1109/tii.2020.3047843 – ident: ref13 doi: 10.1109/BigDataSecurity-HPSC-IDS49724.2020.00027 – ident: ref16 doi: 10.1109/TII.2020.3008010 – ident: ref33 doi: 10.1109/tsc.2018.2859986 – ident: ref47 doi: 10.1145/3038912.3052569 – ident: ref2 doi: 10.1109/JIOT.2020.2974281 – ident: ref19 doi: 10.1109/TSC.2012.31 – ident: ref17 doi: 10.1109/ICWS.2007.140 – ident: ref45 doi: 10.1109/MIC.2003.1167344 – start-page: 5998 volume-title: Poc. Annu. Conf. Neural Inf. Process. Syst. year: 2017 ident: ref40 article-title: Attention is all you need – ident: ref5 doi: 10.1145/3426968 – ident: ref32 doi: 10.1109/tsc.2019.2891517 – volume: 53 start-page: 75 volume-title: Expert Syst. Appl. year: 2016 ident: ref27 article-title: Context-aware QoS prediction for web service recommendation and selection – start-page: 315 volume-title: Proc. 14th Int. Conf. Artif. Intell. Statist. ident: ref41 article-title: Deep sparse rectifier neural networks – ident: ref3 doi: 10.1109/TITS.2019.2900481 – ident: ref9 doi: 10.1109/tetc.2020.2993032
SSID	ssj0006209
Score	2.6896913
Snippet	Deep-Learning-as-a-service (DLaaS) has received increasing attention due to its novelty as a diagram for deploying deep learning techniques. However, DLaaS...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	669
SubjectTerms	Adversarial attacks Computational modeling Deep learning dlaas graph neural network Internet of Things Neural networks Performance evaluation Predictive models probability forecast qos prediction Quality of service Recommender systems Security Uncertainty
Title	QoS Prediction and Adversarial Attack Protection for Distributed Services Under DLaaS
URI	https://ieeexplore.ieee.org/document/10195840 https://www.proquest.com/docview/2924036383
Volume	73
WOSCitedRecordID	wos001167590600015&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: 1557-9956 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0006209 issn: 0018-9340 databaseCode: RIE dateStart: 19680101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA46POjB6Zw4nZKDBy-daZs2zXFsDg9jTLbJbiW_CqJ0snX-_b6k7RjIDkIPhb6U0pf38l7y3vch9Eh1mEEYDpkqT4RHYxl5CY24J7hmBEaocsPtfcwmk2S55NOqWd31whhjXPGZ6dlbd5avV2prt8rAwi00CoUM_ZgxVjZr7dxuXNdz-GDBISUVjo9P-PN8AIlg4PdgPjPXibK3BDlOlT-O2K0uo-Y_v-sCnVdhJO6Xer9ERyZvoWZN0YAri22hsz28wSu0eFvN8HRtz2asPrDINXaMzBth5yHuF4VQnyDhsBusBIS0eGixdS0tltG4di3Y8SXh4ViIWRstRi_zwatX8Sp4KuCk8AKtheJhrH0miRZRwDjENQqSYU50AhGT4STKCFUyY5GNHyRjsMDBs4hLEcThNWrkq9zcICxMKCHGgSxTRDSUUoSKS63gojrWJOugXv2rU1WBjlvui6_UJR-Ep_NBanWTVrrpoKfdgO8Sb-OwaNuqYk-s1EIHdWtlppVBbtKAW-BBcDbh7YFhd-gU3k7L-rIuahTrrblHJ-qn-NisH9xc-wU-ws_n
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB5EBfVgfVSsVt2DBy-pm2STdI-ltVSspdIqvYV9FURppU39_c5uklIQD0IOgcySkNmZndmd-T6AW6bDKYbhmKnypvBYLCOvySLuCa4TiiNUvuH21k8Gg-ZkwodFs7rrhTHGuOIz07C37ixfz9XKbpWhhVtoFIYZ-k7EWODn7VprxxuXFR0-2nDIaIHk41N-P25jKhj4DZzRietF2ViEHKvKL1fs1pdu5Z9fdgSHRSBJWrnmj2HLzE6gUpI0kMJmT-BgA3HwFF5f5iMyXNjTGasRImaaOE7mpbAzkbSyTKgPlHDoDVYCg1rSsei6lhjLaFI6F-IYk0inL8SoCq_dh3G75xXMCp4KOM28QGuheBhrP5FUiyhIOEY2CtNhTnUTYybDaTSlTMlpEtkIQiYJLnH4LOJSBHF4Btuz-cycAxEmlBjlYJ4pIhZKKULFpVZ4MR1rOq1Bo_zVqSpgxy37xWfq0g_K03E7tbpJC93U4G494CtH3PhbtGpVsSGWa6EG9VKZaWGSyzTgFnoQ3U148cewG9jrjZ_7af9x8HQJ-_gmlleb1WE7W6zMFeyq7-x9ubh28-4HOYXTLg
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=QoS+Prediction+and+Adversarial+Attack+Protection+for+Distributed+Services+Under+DLaaS&rft.jtitle=IEEE+transactions+on+computers&rft.au=Liang%2C+Wei&rft.au=Li%2C+Yuhui&rft.au=Xu%2C+Jianlong&rft.au=Zheng%2C+Qin&rft.date=2024-03-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0018-9340&rft.eissn=1557-9956&rft.volume=73&rft.issue=3&rft.spage=669&rft_id=info:doi/10.1109%2FTC.2021.3077738&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9340&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9340&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9340&client=summon