Assessing Deanonymization Risks with Stylometry-Assisted LLM Agent
This work addresses the growing concern of unintended deanonymization risks in textual data for authors and publishers, providing a proactive defense mechanism.
This paper introduces an LLM agent that uses stylometry to assess and mitigate deanonymization risks in textual data like news articles. The SALA method, which combines quantitative stylometric features with LLM reasoning, achieves high inference accuracy on large-scale news datasets, especially when augmented with a database module. The agent also proposes a guided recomposition strategy to reduce authorship identifiability while preserving meaning.
The rapid advancement of large language models (LLMs) has enabled powerful authorship inference capabilities, raising growing concerns about unintended deanonymization risks in textual data such as news articles. In this work, we introduce an LLM agent designed to evaluate and mitigate such risks through a structured, interpretable pipeline. Central to our framework is the proposed $\textit{SALA}$ (Stylometry-Assisted LLM Analysis) method, which integrates quantitative stylometric features with LLM reasoning for robust and transparent authorship attribution. Experiments on large-scale news datasets demonstrate that $\textit{SALA}$, particularly when augmented with a database module, achieves high inference accuracy in various scenarios. Finally, we propose a guided recomposition strategy that leverages the agent's reasoning trace to generate rewriting prompts, effectively reducing authorship identifiability while preserving textual meaning. Our findings highlight both the deanonymization potential of LLM agents and the importance of interpretable, proactive defenses for safeguarding author privacy.