"AUTOLYCUS: Exploiting Explainable AI (XAI) for Model Extraction Attacks ..."

Abdullah Çaglar Öksüz, Anisa Halimi, Erman Ayday (2023)

Details and statistics

DOI: 10.48550/ARXIV.2302.02162

access: open

type: Informal or Other Publication

metadata version: 2023-02-10

a service of  Schloss Dagstuhl - Leibniz Center for Informatics