Private Data Protection with Machine Unlearning in Contrastive Learning Networks

Kongyang Chen, Zixin Wang and Bing Mi ()
Additional contact information
Kongyang Chen: School of Artificial Intelligence, Guangzhou University, Guangzhou 510006, China
Zixin Wang: School of Artificial Intelligence, Guangzhou University, Guangzhou 510006, China
Bing Mi: School of Public Finance and Taxation, Guangdong University of Finance and Economics, Guangzhou 510320, China

Mathematics, 2024, vol. 12, issue 24, 1-17

Abstract: The security of AI models poses significant challenges, as sensitive user information can potentially be inferred from the models, leading to privacy breaches. To address this, machine unlearning methods aim to remove specific data from a trained model, effectively eliminating the training traces of those data. However, most existing approaches focus primarily on supervised learning scenarios, leaving the unlearning of contrastive learning models underexplored. This paper proposes a novel fine-tuning-based unlearning method tailored for contrastive learning models. The approach introduces a third-party dataset to ensure that the model’s outputs for forgotten data align with those of the third-party dataset, thereby removing identifiable training traces. A comprehensive loss function is designed, encompassing three objectives: preserving model accuracy, constraining gradients to make forgotten and third-party data indistinguishable, and reducing model confidence on the third-party dataset. The experimental results demonstrate the effectiveness of the proposed method. Membership inference attacks conducted before and after unlearning show that the forgotten data’s prediction distribution becomes indistinguishable from that of the third-party data, validating the success of the unlearning process. Moreover, the proposed method achieves this with minimal performance degradation, making it suitable for practical applications in privacy-preserving AI.

Keywords: data privacy; machine unlearning; contrastive learning (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/24/4001/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/24/4001/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:24:p:4001-:d:1548375

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().