Make Text Unlearnable: Exploiting Effective Patterns to Protect Personal Data

TL;DR

This paper introduces a practical method to create unlearnable text by extracting simple patterns from optimized noise, protecting personal data in NLP tasks without requiring extensive model access.

Contribution

It extends bi-level optimization for unlearnable text generation by extracting generalizable patterns, making data protection accessible and effective across various models and tasks.

Findings

Unlearnable text remains effective against unknown models.

Patterns are transferable across datasets and tasks.

Open-source tools facilitate widespread adoption.

Abstract

This paper addresses the ethical concerns arising from the use of unauthorized public data in deep learning models and proposes a novel solution. Specifically, building on the work of Huang et al. (2021), we extend their bi-level optimization approach to generate unlearnable text using a gradient-based search technique. However, although effective, this approach faces practical limitations, including the requirement of batches of instances and model architecture knowledge that is not readily accessible to ordinary users with limited access to their own data. Furthermore, even with semantic-preserving constraints, unlearnable noise can alter the text's semantics. To address these challenges, we extract simple patterns from unlearnable text produced by bi-level optimization and demonstrate that the data remains unlearnable for unknown models. Additionally, these patterns are not instance- or dataset-specific, allowing users to readily apply them to text classification and question-answering tasks, even if only a small proportion of users implement them on their public content. We also open-source codes to generate unlearnable text and assess unlearnable noise to benefit the public and future studies.