Vertical Federated Unlearning via Backdoor Certification

TL;DR

This paper proposes a novel method for unlearning specific client data in vertical federated learning using gradient ascent and backdoor verification, achieving results comparable to retraining from scratch.

Contribution

It introduces a new unlearning mechanism in VFL that inverts traditional training to remove client influence without full data access or parameter storage.

Findings

Unlearning closely matches retraining results.

Backdoor mechanism verifies unlearning effectiveness.

Method avoids full data access and parameter storage.

Abstract

Vertical Federated Learning (VFL) offers a novel paradigm in machine learning, enabling distinct entities to train models cooperatively while maintaining data privacy. This method is particularly pertinent when entities possess datasets with identical sample identifiers but diverse attributes. Recent privacy regulations emphasize an individual's \emph{right to be forgotten}, which necessitates the ability for models to unlearn specific training data. The primary challenge is to develop a mechanism to eliminate the influence of a specific client from a model without erasing all relevant data from other clients. Our research investigates the removal of a single client's contribution within the VFL framework. We introduce an innovative modification to traditional VFL by employing a mechanism that inverts the typical learning trajectory with the objective of extracting specific data contributions. This approach seeks to optimize model performance using gradient ascent, guided by a pre-defined constrained model. We also introduce a backdoor mechanism to verify the effectiveness of the unlearning procedure. Our method avoids fully accessing the initial training data and avoids storing parameter updates. Empirical evidence shows that the results align closely with those achieved by retraining from scratch. Utilizing gradient ascent, our unlearning approach addresses key challenges in VFL, laying the groundwork for future advancements in this domain. All the code and implementations related to this paper are publicly available at https://github.com/mengde-han/VFL-unlearn.