Robust Utility-Preserving Text Anonymization Based on Large Language Models
Abstract: Text anonymization is crucial for sharing sensitive data while maintaining privacy. Existing techniques face the emerging challenges of re-identification attack ability of Large Language Models (LLMs), which have shown advanced capability in memorizing detailed information and patterns as well as connecting disparate pieces of information. In defending against LLM-based re-identification attacks, anonymization could jeopardize the utility of the resulting anonymized data in downstream tasks---the trade-off between privacy and data utility requires deeper understanding within the context of LLMs. This paper proposes a framework composed of three LLM-based components---a privacy evaluator, a utility evaluator, and an optimization component, which work collaboratively to perform anonymization. To provide a practical model for large-scale and real-time environments, we distill the anonymization capabilities into a lightweight model using Direct Preference Optimization (DPO). Extensive experiments demonstrate that the proposed models outperform baseline models, showing robustness in reducing the risk of re-identification while preserving greater data utility in downstream tasks.
Paper Type: Long
Research Area: Language Modeling
Research Area Keywords: text anonymization, security and privacy, large language model
Contribution Types: Model analysis & interpretability, NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources
Languages Studied: English
Submission Number: 409
Loading