I Am No One: Style-Aware Paraphrasing for Text Anonymization

2026-09-10

AI Summary

针对文本匿名化中的隐私风险，提出一种风格感知、基于提示的重写方法，使用预训练大语言模型来构建风格简档并重写文本以抑制可识别风格标记，同时保持内容质量。

Abstract

Authorship attribution models can re-identify users from seemingly anonymized text by exploiting stable stylistic fingerprints, even after explicit identifiers are removed, posing a growing privacy risk for text publishing and analytics. This risk extends to speech-derived text such as ASR transcripts of meetings and call-center conversations, where stylometric leakage can persist even after acoustic anonymization. Differential privacy-based anonymization often severely degrades text quality and utility. We propose a style-aware, prompt-driven anonymization approach that uses pretrained large language models to construct compact stylistic profiles from minimal samples and rewrite text to suppress identifiable style markers while preserving meaning. Across blog and review datasets, our approach reduces authorship attribution F1 by 60-70% while maintaining content quality and readability, substantially outperforming DP-based and non-DP baselines.

Problem

• authorship attribution
• privacy risk
• text anonymization
• stylometric leakage

Innovation

• style-aware
• paraphrasing
• text anonymization
• large language models