用风格分析+大模型判断文本作者，帮用户防泄露
Assessing Deanonymization Risks with Stylometry-Assisted LLM Agent
- 结合文本风格特征与大模型推理，实现可解释的作者识别
- 在新闻数据集上准确率高，数据库增强后效果更优
- 能自动生成改写提示，降低身份暴露风险
大型语言模型（LLM）的快速发展带来了强大的作者溯源能力，引发了新闻等文本数据中意外去匿名化的担忧。本文提出一种用于评估和缓解此类风险的LLM代理，核心是提出的SALA（风格辅助的大模型分析）方法，将定量风格特征与大模型推理相结合，实现鲁棒且透明的作者归属。大规模新闻数据集上的实验表明，SALA在多种场景下均表现出高推理准确率，尤其在引入数据库模块后效果更佳。最后，我们提出一种基于代理推理轨迹的引导式重写策略，通过生成改写提示，有效降低作者可识别性，同时保持文本语义不变。研究揭示了LLM代理在去匿名化方面的潜力，强调了可解释、主动防御对保护作者隐私的重要性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。