Vertical Machine Unlearning: Selectively Removing Sensitive Information From Latent Feature Space release_a7ilytvcizdjrav5bigyc5g37u

by Tao Guo, Song Guo, Jiewei Zhang, Wenchao Xu, Junxiao Wang

Released as a article .

2022  

Abstract

Recently, the enactment of privacy regulations has promoted the rise of machine unlearning paradigm. Most existing studies mainly focus on removing unwanted data samples from a learnt model. Yet we argue that they remove overmuch information of data samples from latent feature space, which is far beyond the sensitive feature scope that genuinely needs to be unlearned. In this paper, we investigate a vertical unlearning mode, aiming at removing only sensitive information from latent feature space. First, we introduce intuitive and formal definitions for this unlearning and show its orthogonal relationship with existing horizontal unlearning. Secondly, given the fact of lacking general solutions to vertical unlearning, we introduce a ground-breaking solution based on representation detachment, where the task-related information is encouraged to retain while the sensitive information is progressively forgotten. Thirdly, observing that some computation results during representation detachment are hard to obtain in practice, we propose an approximation with an upper bound to estimate it, with rigorous theoretical analysis. We validate our method by spanning several datasets and models with prevailing performance. We envision this work as a necessity for future machine unlearning system and an essential component of the latest privacy-related legislation.
In text/plain format

Archived Content

There are no accessible files associated with this release. You could check other releases for this work for an accessible version.

"Dark" Preservation Only
Save Paper Now!

Know of a fulltext copy of on the public web? Submit a URL and we will archive it

Type  article
Stage   submitted
Date   2022-02-27
Version   v1
Language   en ?
arXiv  2202.13295v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 31f846d5-c292-40b9-aa90-7c961fc5d796
API URL: JSON