Machine Unlearning: Solutions and Challenges

Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy breaches, security vulnerabilities, and performance degradation. To address these issues, machine unlearning has emerged as a critical technique to selectively remove specific train...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on emerging topics in computational intelligence Jg. 8; H. 3; S. 2150 - 2168
Hauptverfasser:	Xu, Jie, Wu, Zihan, Wang, Cong, Jia, Xiaohua
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Piscataway IEEE 01.06.2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Adaptation models Computational modeling Data models Data points Machine learning machine learning security Machine unlearning Performance degradation Predictive models Random forests Taxonomy the right to be forgotten Training data
ISSN:	2471-285X, 2471-285X
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!