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.

翻译：大型语言模型（LLM）的快速发展赋予了强大的作者身份推断能力，引发了人们对新闻文章等文本数据中非预期去匿名化风险的日益关注。本研究提出一种LLM代理，旨在通过结构化、可解释的流程评估并缓解此类风险。我们框架的核心是提出的$\textit{SALA}$（风格计量辅助的LLM分析）方法，该方法将定量风格计量特征与LLM推理相结合，实现鲁棒且透明的作者归属判定。在大规模新闻数据集上的实验表明，$\textit{SALA}$方法——尤其在增强数据库模块后——能在多种场景下实现高推断准确率。最后，我们提出一种引导式重构策略，该策略利用代理的推理轨迹生成改写提示，在保持文本语义的同时有效降低作者身份可识别性。我们的研究结果既揭示了LLM代理的去匿名化潜力，也强调了可解释的主动防御机制对于保护作者隐私的重要性。