Efficient Two-stage Model Retraining for Machine Unlearning
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4360-4368
Abstract
With the rise of the General Data Protection Regulation (GDPR), user data holders should guarantee the "individual’s right to be forgotten". It means user data holders must completely remove user data when they receive the request. However, enabling a deep learning model to exclude specific data used during training is challenging. We cannot easily define the meaning of "forgetting" in deep learning and how to achieve it. To address this issue, we propose an efficient machine unlearning architecture to be used for computer vision classification models. Our approach consists of two-stage models, where in the first stage we enables a deep learning model that loses information with contrastive labels in the requested dataset. Second, we retrain the first stage output model with knowledge distillation (KD). Using this two-stage approach, we can substantiate the removal or forgetness of the requested dataset in the deep learning model. With various datasets used for multimedia applications, we demonstrate that our approach achieves performance on par or even higher accuracy than the original model, while effectively removing the requested data.Keywords
Funding Information
- Sungkyunkwan University
- National Research Foundation
This publication has 6 references indexed in Scilit:
- Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations2020
- On the Efficacy of Knowledge Distillation2019
- Humans forget, machines remember: Artificial intelligence and the Right to Be ForgottenComputer Law & Security Review, 2018
- The Right to be Forgotten in the Media: A Data-Driven StudyProceedings on Privacy Enhancing Technologies, 2016
- Towards Making Systems Forget with Machine Unlearning2015
- The EU Proposal for a General Data Protection Regulation and the roots of the ‘right to be forgotten’Computer Law & Security Review, 2013