Machine Unlearning in Generative AI: A Survey
Generative AI technologies have been deployed in many places, such as (multimodal) large language models and vision generative models. Their remarkable performance should be attributed to massive training data and emergent reasoning abilities. However, the models would memorize and generate sensitive, biased, or dangerous information originated from the training data especially those from web crawl. New machine unlearning (MU) techniques are being developed to reduce or eliminate undesirable knowledge and its effects from the models, because those that were designed for traditional classification tasks could not be applied for Generative AI. We offer a comprehensive survey on many things about MU in Generative AI, such as a new problem formulation, evaluation methods, and a structured discussion on the advantages and limitations of different kinds of MU techniques. It also presents several critical challenges and promising directions in MU research. A curated list of readings can be found: https://github.com/franciscoliu/GenAI-MU-Reading.
Code (1)
Tasks
Machine UnlearningSurveySimilar Papers 제목 키워드 기반
A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction
With the rapid advancement of generative models, associated privacy concerns have attracted growing attention. To address this, researchers have begun adapting machine unlearning techniques from traditional classificatio…
Reinforcement LearningMachine Unlearning for Traditional Models and Large Language Models: A Short Survey
With the implementation of personal data privacy regulations, the field of machine learning (ML) faces the challenge of the "right to be forgotten". Machine unlearning has emerged to address this issue, aiming to delete …
Machine UnlearningSurveySurvey of Security and Data Attacks on Machine Unlearning In Financial and E-Commerce
This paper surveys the landscape of security and data attacks on machine unlearning, with a focus on financial and e-commerce applications. We discuss key privacy threats such as Membership Inference Attacks and Data Rec…
Data PoisoningMachine UnlearningMachine Unlearning: A Comprehensive Survey
As the right to be forgotten has been legislated worldwide, many studies attempt to design unlearning mechanisms to protect users' privacy when they want to leave machine learning service platforms. Specifically, machine…
Machine UnlearningSurveySoK: Machine Unlearning for Large Language Models
Large language model (LLM) unlearning has become a critical topic in machine learning, aiming to eliminate the influence of specific training data or knowledge without retraining the model from scratch. A variety of tech…
Large Language ModelMachine UnlearningModel Editing