Threats, Attacks, and Defenses in Machine Unlearning: A Survey
Top Cited Papers
Open Access
- 18 February 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Computer Society
- Vol. 6, 413-425
Abstract
Machine Unlearning (MU) has recently gained considerable attention due to its potential to achieve Safe AI by removing the influence of specific data from trained Machine Learning (ML) models. This process, known as knowledge removal, addresses AI governance concerns of training data such as quality, sensitivity, copyright restrictions, obsolescence, and compliance with privacy regulations. Efforts have been made to design efficient unlearning approaches, with MU services being examined for integration with existing machine learning as a service (MLaaS), allowing users to submit requests to remove specific data from the training corpus. However, recent research highlights vulnerabilities in machine unlearning systems that can lead to significant security and privacy concerns. Moreover, extensive research indicates that unlearning methods and prevalent attacks fulfill diverse roles within MU systems. This underscores the intricate relationship and complex interplay among these mechanisms in maintaining system functionality and safety. This survey aims to fill the gap between the extensive number of studies on threats, attacks, and defenses in machine unlearning and the absence of a comprehensive review that categorizes their taxonomy, methods, and solutions, thus offering valuable insights for future research directions and practical implementations.Keywords
All Related Versions
Funding Information
- National Research Foundation
- Singapore and Infocomm Media Development Authority
- Tech Funding Initiative and Strategic Capability Research Centres Funding Initiative
This publication has 61 references indexed in Scilit:
- A survey on machine unlearning: Techniques and new emerged privacy risksJournal of Information Security and Applications, 2025
- Digital security by designSecurity Journal, 2024
- FedCIO: Efficient Exact Federated Unlearning with Clustering, Isolation, and One-shot Aggregation2023
- CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning2023
- Label‐only membership inference attacks on machine unlearning without dependence of posteriorsInternational Journal of Intelligent Systems, 2022
- Federated Knowledge Distillation2022
- Super-forecasting the ‘technological singularity’ risks from artificial intelligenceEvolving Systems, 2022
- Deep Leakage from Gradients2020
- BadNets: Evaluating Backdooring Attacks on Deep Neural NetworksIEEE Access, 2019
- MLaaS: Machine Learning as a Service2015