A Taxonomic Survey of Model Extraction Attacks
| dc.contributor.author | Genç, Didem | |
| dc.contributor.author | Özuysal, Mustafa | |
| dc.contributor.author | Tomur, Emrah | |
| dc.date.accessioned | 2023-11-11T08:54:56Z | |
| dc.date.available | 2023-11-11T08:54:56Z | |
| dc.date.issued | 2023 | |
| dc.description | IEEE International Conference on Cyber Security and Resilience (CSR) -- JUL 31-AUG 02, 2023 -- Venice, ITALY | en_US |
| dc.description.abstract | A model extraction attack aims to clone a machine learning target model deployed in the cloud solely by querying the target in a black-box manner. Once a clone is obtained it is possible to launch further attacks with the aid of the local model. In this survey, we analyze existing approaches and present a taxonomic overview of this field based on several important aspects that affect attack efficiency and performance. We present both early works and recently explored directions. We conclude with an analysis of future directions based on recent developments in machine learning methodology. | en_US |
| dc.description.sponsorship | IEEE,IEEE Syst, Man, & Cybernet Soc,LOGOS Res & Innovat,Thales,DARIAH IT,Binare,Citta Metropolitana Venezia,Consorzio Interuniversitario Nazl Informatica,European Cyber Secur Org, Women 4Cyber,MITRE,IEEE SMC Italian Chapter,Ctr Cyber Secur & Int Relat Studies,IEEE TEMS,Cyber 4.0 Cybersecur Competence Ctr,Integrated Miss Grp Secur,DHLAB Univ Roma Tre | en_US |
| dc.description.sponsorship | Scientific and Technological Research Council of Turkey (TUBITAK) through the 1515 Frontier Research and Development Laboratories Support Program [5169902] | en_US |
| dc.description.sponsorship | This work was supported in part by The Scientific and Technological Research Council of Turkey (TUBITAK) through the 1515 Frontier Research and Development Laboratories Support Program under Project 5169902. | en_US |
| dc.identifier.doi | 10.1109/CSR57506.2023.10224959 | |
| dc.identifier.isbn | 9798350311709 | |
| dc.identifier.scopus | 2-s2.0-85171777851 | |
| dc.identifier.uri | https://doi.org/10.1109/CSR57506.2023.10224959 | |
| dc.identifier.uri | https://hdl.handle.net/11147/13969 | |
| dc.language.iso | en | en_US |
| dc.publisher | IEEE | en_US |
| dc.relation.ispartof | 2023 IEEE International Conference On Cyber Security and Resilience, Csr | en_US |
| dc.rights | info:eu-repo/semantics/closedAccess | en_US |
| dc.title | A Taxonomic Survey of Model Extraction Attacks | en_US |
| dc.type | Conference Object | en_US |
| dspace.entity.type | Publication | |
| gdc.author.scopusid | 57212107327 | |
| gdc.author.scopusid | 9843586600 | |
| gdc.author.scopusid | 6504092986 | |
| gdc.bip.impulseclass | C5 | |
| gdc.bip.influenceclass | C5 | |
| gdc.bip.popularityclass | C4 | |
| gdc.coar.access | metadata only access | |
| gdc.coar.type | text::conference output | |
| gdc.collaboration.industrial | true | |
| gdc.description.department | İzmir Institute of Technology | en_US |
| gdc.description.departmenttemp | [Genc, Didem; Ozuysal, Mustafa] Izmir Inst Technol, Comp Engn Dept, TR-35430 Izmir, Turkiye; [Tomur, Emrah] Ericsson Res, TR-34390 Istanbul, Turkiye | en_US |
| gdc.description.endpage | 205 | en_US |
| gdc.description.publicationcategory | Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı | en_US |
| gdc.description.startpage | 200 | en_US |
| gdc.identifier.openalex | W4386214368 | |
| gdc.identifier.wos | WOS:001062143200032 | |
| gdc.index.type | WoS | |
| gdc.index.type | Scopus | |
| gdc.oaire.diamondjournal | false | |
| gdc.oaire.impulse | 2.0 | |
| gdc.oaire.influence | 2.7136358E-9 | |
| gdc.oaire.isgreen | true | |
| gdc.oaire.popularity | 4.4427626E-9 | |
| gdc.oaire.publicfunded | false | |
| gdc.openalex.collaboration | International | |
| gdc.openalex.fwci | 1.78810021 | |
| gdc.openalex.normalizedpercentile | 0.84 | |
| gdc.opencitations.count | 3 | |
| gdc.plumx.mendeley | 7 | |
| gdc.plumx.scopuscites | 7 | |
| gdc.scopus.citedcount | 7 | |
| gdc.wos.citedcount | 3 | |
| relation.isAuthorOfPublication.latestForDiscovery | c5de0144-5a8c-4c0a-93b2-334507777064 | |
| relation.isOrgUnitOfPublication.latestForDiscovery | 9af2b05f-28ac-4014-8abe-a4dfe192da5e |