Privacy-preserving explainable AI:a survey  

作　　者：Thanh Tam NGUYEN Thanh Trung HUYNH Zhao REN Thanh Toan NGUYEN Phi Le NGUYEN Hongzhi YIN Quoc Viet Hung NGUYEN 

机构地区：[1]School of Information and Communication Technology,Griffith University,Gold Coast QLD 4215,Australia [2]School of Computer and Communication Sciences,Ecole Polytechnique Federale de Lausanne,Lausanne 1015,Switzerland [3]Faculty of Mathematics and Computer Science,University of Bremen,Bremen 28359,Germany [4]Faculty of Information Technology,HUTECH University,Ho Chi Minh City 70000,Vietnam [5]Department of Computer Science,Hanoi University of Science and Technology,Hanoi 10000,Vietnam [6]School of Electrical Engineering and Computer Science,The University of Queensland,Brisbane QLD 4072,Australia

出　　处：《Science China(Information Sciences)》2025年第1期20-53,共34页中国科学(信息科学)(英文版)

基　　金：supported by ARC Discovery Early Career Researcher Award(Grant No.DE200101465);ARC DP Project(Grant No.DP240101108).

摘　　要：As the adoption of explainable AI(XAI)continues to expand,the urgency to address its privacy implications intensifies.Despite a growing corpus of research in AI privacy and explainability,there is little attention on privacy-preserving model explanations.This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures.Our contribution to this field comprises a thorough analysis of research papers with a connected taxonomy that facilitates the categorization of privacy attacks and countermeasures based on the targeted explanations.This work also includes an initial investigation into the causes of privacy leaks.Finally,we discuss unresolved issues and prospective research directions uncovered in our analysis.This survey aims to be a valuable resource for the research community and offers clear insights for those new to this domain.To support ongoing research,we have established an online resource repository,which will be continuously updated with new and relevant findings.

关 键 词：privacy-preserving explainable AI privacy attacks privacy defences PrivEx PPXAI 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP309.7[自动化与计算机技术—控制科学与工程]