Machine Unlearning for Document Classification

TL;DR

This paper introduces the first study of machine unlearning in document classification, enabling models to forget specific data to enhance privacy while maintaining performance.

Contribution

It pioneers applying machine unlearning techniques to document classification, addressing privacy concerns with a realistic server-side scenario.

Findings

First investigation into machine unlearning for document classification

Proposes a practical scenario with limited data access for efficient forgetting

Code is publicly available for reproducibility

Abstract

Document understanding models have recently demonstrated remarkable performance by leveraging extensive collections of user documents. However, since documents often contain large amounts of personal data, their usage can pose a threat to user privacy and weaken the bonds of trust between humans and AI services. In response to these concerns, legislation advocating ``the right to be forgotten" has recently been proposed, allowing users to request the removal of private information from computer systems and neural network models. A novel approach, known as machine unlearning, has emerged to make AI models forget about a particular class of data. In our research, we explore machine unlearning for document classification problems, representing, to the best of our knowledge, the first investigation into this area. Specifically, we consider a realistic scenario where a remote server houses a well-trained model and possesses only a small portion of training data. This setup is designed for efficient forgetting manipulation. This work represents a pioneering step towards the development of machine unlearning methods aimed at addressing privacy concerns in document analysis applications. Our code is publicly available at \url{https://github.com/leitro/MachineUnlearning-DocClassification}.