A Certified Unlearning Approach without Access to Source Data

TL;DR

This paper introduces a certified unlearning method that removes data from trained models without needing access to the original data, using surrogate datasets and statistical distance measures.

Contribution

It presents a novel framework for data unlearning that operates without source data, providing theoretical guarantees and practical noise calibration techniques.

Findings

Effective data removal demonstrated on synthetic datasets

Maintains model utility while ensuring privacy guarantees

Theoretical bounds support practical implementation

Abstract

With the growing adoption of data privacy regulations, the ability to erase private or copyrighted information from trained models has become a crucial requirement. Traditional unlearning methods often assume access to the complete training dataset, which is unrealistic in scenarios where the source data is no longer available. To address this challenge, we propose a certified unlearning framework that enables effective data removal \final{without access to the original training data samples}. Our approach utilizes a surrogate dataset that approximates the statistical properties of the source data, allowing for controlled noise scaling based on the statistical distance between the two. \updated{While our theoretical guarantees assume knowledge of the exact statistical distance, practical implementations typically approximate this distance, resulting in potentially weaker but still meaningful privacy guarantees.} This ensures strong guarantees on the model's behavior post-unlearning while maintaining its overall utility. We establish theoretical bounds, introduce practical noise calibration techniques, and validate our method through extensive experiments on both synthetic and real-world datasets. The results demonstrate the effectiveness and reliability of our approach in privacy-sensitive settings.