东华大学学报（英文版）2026，Vol.43Issue(4)：49-58,10.DOI:10.19884/j.1672-5220.202505004
黑盒模型反演攻击的研究综述
Review of Research on Black-Box Model Inversion Attack
摘要
Abstract
The development of artificial intelligence has given rise to the paradigm of machine learning as a service,enabling users to either train the requisite models or employ pre-existing models to make predictions based on the training data that users provide.Despite various measures taken to prevent privacy leakage in machine learning,such as data deletion and anonymization,model inversion attack(MIA)remains capable of inferring sensitive information from user data to a certain extent.This paper reviews the current state of research on black-box MIA,with a particular focus on confidence-based MIA and label-based MIA.It further analyzes the MIA methodologies applied to the emerging modes such as text and audio in recent years,filling the gap in the current review of such modes.Finally,the paper discusses the future challenges and research directions for black-box MIA.关键词
机器学习/模型反演攻击/黑盒模型/隐私保护Key words
machine learning/model inversion attack/black-box model/privacy protection分类
信息技术与安全科学引用本文复制引用
何世飞,王晨,罗辛,徐光伟..黑盒模型反演攻击的研究综述[J].东华大学学报（英文版）,2026,43(4):49-58,10.基金项目
Natural Science Foundation of Shanghai,China(No.19ZR1402000) （No.19ZR1402000）
