Please use this identifier to cite or link to this item: https://hdl.handle.net/11147/13969
Title: A Taxonomic Survey of Model Extraction Attacks
Authors: Genç, Didem
Özuysal, Mustafa
Tomur, Emrah
Publisher: IEEE
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.
Description: IEEE International Conference on Cyber Security and Resilience (CSR) -- JUL 31-AUG 02, 2023 -- Venice, ITALY
URI: https://doi.org/10.1109/CSR57506.2023.10224959
https://hdl.handle.net/11147/13969
ISBN: 979-8-3503-1170-9
Appears in Collections:Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Show full item record



CORE Recommender

Page view(s)

362
checked on May 20, 2024

Google ScholarTM

Check




Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.