AUTOLYCUS: Exploiting Explainable AI (XAI) for Model Extraction Attacks against Interpretable Models

4 February 2023

Papers citing "AUTOLYCUS: Exploiting Explainable AI (XAI) for Model Extraction Attacks against Interpretable Models"

8 / 8 papers shown

Title
DualCF: Efficient Model Extraction Attack from Counterfactual Explanations Yongjie Wang Hangwei Qian Chunyan Miao AAML 24 31 0 13 May 2022
MEGEX: Data-Free Model Extraction Attack against Gradient-Based Explainable AI T. Miura Satoshi Hasegawa Toshiki Shibahara SILM MIACV 34 37 0 19 Jul 2021
Exploiting Explanations for Model Inversion Attacks Xu Zhao Wencan Zhang Xiao Xiao Brian Y. Lim MIACV 41 83 0 26 Apr 2021
Label-Only Membership Inference Attacks Christopher A. Choquette-Choo Florian Tramèr Nicholas Carlini Nicolas Papernot MIACV MIALM 47 500 0 28 Jul 2020
Exploring Connections Between Active Learning and Model Extraction Varun Chandrasekaran Kamalika Chaudhuri Irene Giacomelli Shane Walker Songbai Yan MIACV 91 158 0 05 Nov 2018
Membership Inference Attacks against Machine Learning Models Reza Shokri M. Stronati Congzheng Song Vitaly Shmatikov SLR MIALM MIACV 191 4,075 0 18 Oct 2016
Learning Deep Features for Discriminative Localization Bolei Zhou A. Khosla Àgata Lapedriza A. Oliva Antonio Torralba SSL SSeg FAtt 91 9,266 0 14 Dec 2015
Agnostic Active Learning Without Constraints A. Beygelzimer Daniel J. Hsu John Langford Tong Zhang VLM 79 181 0 14 Jun 2010