BlindU: Blind Machine Unlearning Without Revealing Erasing Data
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-05 · 48 (5) · 5963-5978
DOI: 10.1109/tpami.2026.3654093 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-05. Verfasst von Weiqi Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: Australia ARC.
Abstract (Originalsprache)
Machine unlearning enables data holders to remove the contribution of their specified samples from trained models to protect their privacy. However, it is paradoxical that most unlearning methods require the unlearning requesters to first upload their data to the server as a prerequisite for unlearning. These methods are infeasible in many privacy-preserving scenarios where servers are prohibited from accessing users' data, such as federated learning (FL). In this paper, we explore how to implement unlearning under the condition of not uncovering the erasing data to the server. We propose Blind Unlearning (BlindU), which carries out unlearning using compressed representations instead of original inputs. BlindU only involves the server and the unlearning user: the user locally generates privacy-preserving representations, and the server performs unlearning solely on these representations and their labels. For the FL model training, we employ the information bottleneck (IB) mechanism. The encoder of the IB-based FL model learns representations that distort maximum task-irrelevant information from inputs, allowing FL users to generate compressed representations locally. For effective unlearning using compressed representation, BlindU integrates two dedicated unlearning modules tailored explicitly for IB-based models and uses a multiple gradient descent algorithm to balance forgetting and utility retaining. While IB compression already provides protection for task-irrelevant information of inputs, to further enhance the privacy protection, we introduce a noise-free differential privacy (DP) masking method to deal with the raw erasing data before compressing. Theoretical analysis and extensive experimental results illustrate the superiority of BlindU in privacy protection and unlearning effectiveness compared with the best existing privacy-preserving unlearning benchmarks.
Förderung
- Australia ARC
Zitieren
APA
Wang, W., Tian, Z., Zhang, C., & Yu, S. (2026). BlindU: Blind Machine Unlearning Without Revealing Erasing Data. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(5), 5963-5978. https://doi.org/10.1109/tpami.2026.3654093
Vancouver
Wang W, Tian Z, Zhang C, Yu S. BlindU: Blind Machine Unlearning Without Revealing Erasing Data. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(5):5963-5978. doi:10.1109/tpami.2026.3654093
BibTeX
@article{Wang2026,
author = {Wang, Weiqi and Tian, Zhiyi and Zhang, Chenhan and Yu, Shui},
title = {BlindU: Blind Machine Unlearning Without Revealing Erasing Data},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {5},
pages = {5963--5978},
doi = {10.1109/tpami.2026.3654093}
}
EUVIMED