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

TL;DR

This paper investigates vulnerabilities in machine unlearning services within MLaaS, revealing how over-unlearning can compromise model utility and privacy, and proposing strategies to measure and exploit these risks.

Contribution

It introduces two novel black-box strategies to assess the impact of over-unlearning, exposing security risks in current machine unlearning approaches.

Findings

Over-unlearning can significantly degrade model performance.

Proposed strategies effectively measure unlearning impact.

Results highlight security vulnerabilities in existing unlearning methods.

Abstract

The right to be forgotten requires the removal or "unlearning" of a user's data from machine learning models. However, in the context of Machine Learning as a Service (MLaaS), retraining a model from scratch to fulfill the unlearning request is impractical due to the lack of training data on the service provider's side (the server). Furthermore, approximate unlearning further embraces a complex trade-off between utility (model performance) and privacy (unlearning performance). In this paper, we try to explore the potential threats posed by unlearning services in MLaaS, specifically over-unlearning, where more information is unlearned than expected. We propose two strategies that leverage over-unlearning to measure the impact on the trade-off balancing, under black-box access settings, in which the existing machine unlearning attacks are not applicable. The effectiveness of these strategies is evaluated through extensive experiments on benchmark datasets, across various model architectures and representative unlearning approaches. Results indicate significant potential for both strategies to undermine model efficacy in unlearning scenarios. This study uncovers an underexplored gap between unlearning and contemporary MLaaS, highlighting the need for careful considerations in balancing data unlearning, model utility, and security.