A Survey of Machine Unlearning in Generative AI Models: Methods, Applications, Security, and Challenges

An Huang, Zhipeng Cai, Zuobin Xiong

Abstract: Generative AI has flourished over the past decade, with generative models advancing in both the industrial and academic sectors. Given various applications, some scenarios have seen the misuse of generative AI, particularly in the integration with the Internet of Things (IoT). IoT devices often handle personal and sensitive data, raising serious concerns about privacy leakage and security breaches when generating data. As a promising countermeasure, machine unlearning has emerged to solve the problems posed by these generative models by effectively removing specific concepts or sensitive information from trained models. In this survey, anchored in generative models, machine unlearning approaches are reviewed, categorized, and discussed comprehensively and systematically. Existing unlearning approaches are classified into gradient-based techniques, task vectors, knowledge distillation, data sharding, and reliable unlearning methods. Apart from previous works, this survey extends the review of attack methods that aim to exploit the vulnerability in generative models and assess the robustness of these unlearning methods. In addition, popular metrics and datasets in machine unlearning research are summarized and evaluated based on effectiveness, efficiency, and security. Finally, we shed light on the future directions of this emerging research topic by discussing applications, highlighting challenges, and exploring research frontiers for the current machine unlearning community and the new investigators to come.

External IDs:dblp:journals/iotj/HuangCX25