A Review on Machine Unlearning

• Published in: SN computer science Vol. 4; no. 4; p. 337
• Main Authors: Zhang, Haibo, Nakamura, Toru, Isohara, Takamasa, Sakurai, Kouichi
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 19.04.2023; Springer Nature B.V
• Subjects: Algorithms; Artificial intelligence; Big Data; Computer Imaging; Computer Science; Computer Systems Organization and Communication Networks; Data analysis; Data Structures and Information Theory; Datasets; General Data Protection Regulation; Information Systems and Communication Service; Internet; Machine learning; Pattern Recognition and Graphics; Privacy; Research methodology; Search engines; Security; Software Engineering/Programming and Operating Systems; Survey Article; Vision; Machine unlearning; Data lineage; Privacy; Security; Machine learning
• ISSN: 2661-8907; 2662-995X; 2661-8907
• DOI: 10.1007/s42979-023-01767-4

Recently, an increasing number of laws have governed the useability of users’ privacy. For example, Article 17 of the General Data Protection Regulation (GDPR), the right to be forgotten , requires machine learning applications to remove a portion of data from a dataset and retrain it if the user makes such a request. Furthermore, from the security perspective, training data for machine learning models, i.e., data that may contain user privacy, should be effectively protected, including appropriate erasure. Therefore, researchers propose various privacy-preserving methods to deal with such issues as machine unlearning. This paper provides an in-depth review of the security and privacy concerns in machine learning models. First, we present how machine learning can use users’ private data in daily life and the role that the GDPR plays in this problem. Then, we introduce the concept of machine unlearning by describing the security threats in machine learning models and how to protect users’ privacy from being violated using machine learning platforms. As the core content of the paper, we introduce and analyze current machine unlearning approaches and several representative results and discuss them in the context of the data lineage. Furthermore, we also discuss the future research challenges in this field.