通过风格学辅助LLM代理评估去匿名化风险
Assessing Deanonymization Risks with Stylometry-Assisted LLM Agent
AI总结:
本文提出SLA方法,通过风格学与LLM推理结合,评估和缓解文本去匿名化风险,实验表明其在各类场景中具有高推断准确性,并提出引导重组成策略以降低作者身份可识别性。
摘要:
大语言模型(LLMs)的快速发展使作者身份推断能力显著增强,引发了对文本数据(如新闻文章)中意外去匿名化风险的日益增长的担忧。在本工作中,我们引入了一个LLM代理,通过结构化且可解释的流程来评估和缓解此类风险。我们的框架核心是提出的方法SLA(风格学辅助LLM分析),它整合了定量风格学特征与LLM推理,以实现稳健且透明的作者身份归因。在大规模新闻数据集上的实验表明,SLA,特别是当配备数据库模块时,在各种场景中实现了高推断准确性。最后,我们提出了一种引导重组成策略,利用代理的推理轨迹生成重写提示,有效降低作者身份可识别性,同时保持文本意义。我们的发现突显了LLM代理的去匿名化潜力以及可解释、主动防御在保护作者隐私中的重要性。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。