English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The right to be forgotten requires the removal or "unlearning" of a user'sdata from machine learning models. However, in the context of Machine Learningas a Service (MLaaS), retraining a model from scratch to fulfill the unlearningrequest is impractical due to the lack of training data on the serviceprovider's side (the server). Furthermore, approximate unlearning furtherembraces a complex trade-off between utility (model performance) and privacy(unlearning performance). In this paper, we try to explore the potentialthreats posed by unlearning services in MLaaS, specifically over-unlearning,where more information is unlearned than expected. We propose two strategiesthat leverage over-unlearning to measure the impact on the trade-off balancing,under black-box access settings, in which the existing machine unlearningattacks are not applicable. The effectiveness of these strategies is evaluatedthrough extensive experiments on benchmark datasets, across various modelarchitectures and representative unlearning approaches. Results indicatesignificant potential for both strategies to undermine model efficacy inunlearning scenarios. This study uncovers an underexplored gap betweenunlearning and contemporary MLaaS, highlighting the need for carefulconsiderations in balancing data unlearning, model utility, and security.

A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services