This work proposes 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.
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.
Online users often release multiple texts under the same identity, giving attackers an author profile that can reveal more than any single text. Existing authorship obfuscation methods optimize privacy independently for each document, leaving them blind to cross-document correlations that make aggregation dangerous. We...
Qian Ma, A. Squicciarini, Sarah Rajtmajer· 0 citations
Large language models (LLMs) have demonstrated the ability to generate user-specific text with high stylistic fidelity. However, the personal data that enables such personalization frequently embeds demographic, cultural, and stylistic markers that raises concerns about stylometric re- identification. This paper invest...
AuthBench is introduced, a large-scale multilingual benchmark for authorship representation that is designed to make this evaluation broad, standardized, and realistic, and position it not only as a new benchmark, but as a diagnostic resource for studying when and why authorship representations succeed or fail.
Mao-Xun Huang, Zhen-Xing Zhang, C. Cardie· 0 citations
Authorship verification in social media text is a growing challenge in digital forensics, yet existing stylometric approaches rely on textual features that degrade substantially when reference and questioned texts originate from different communicative contexts. This study investigates whether emoji usage patterns-a pe...
Yasin Etli, Ahmet Özdil, M. Aşırdizer· Forensic Science Internation...· 0 citations
Model-attribution classifiers can often identify which language model produced a text, making model-specific writing patterns a signal of provenance. Accurate attribution on unmodified text, however, does not show whether the prediction still identifies the original source after deliberate rewriting. We formulate this...
Hao-Han Yuan, Si-Min Chen, Xi Niu et al.· 0 citations
This survey provides the first comprehensive and systematic review of text anonymization methods published between 2020 and 2025, covering 48 primary studies identified through a structured search and rigorous screening procedure and reveals a growing shift from identifier‐centric de‐identification toward context‐aware...
Marina Litvak, A. Jorge· WIREs Data Mining and Knowle...· 0 citations
