Urania在保护隐私的前提下，从大模型对话中提取有效洞察。
Urania: Differentially Private Insights into AI Use
- 通过私有聚类与多种关键词提取方法实现差分隐私
- 在保持语义相似性的同时，显著提升隐私保护能力
- 适合关注用户数据安全的研究者与产品开发者
我们提出Urania，一种具备严格差分隐私（DP）保障的LLM聊天机器人交互洞察生成框架。该框架采用私有聚类机制与创新的关键词提取方法，包括基于频率、TF-IDF和大模型引导的方法。通过聚类、分区选择及基于直方图的汇总等DP工具，实现端到端隐私保护。评估涵盖词汇与语义内容保留度、对话对相似性以及大模型指标，对比了非私有的Clio-inspired管道（Tamkin et al., 2024）。此外，我们构建了一种简单经验隐私评估，验证了DP管道的鲁棒性提升。结果表明，Urania能在确保严格用户隐私的同时，有效提取有意义的对话洞察，实现数据效用与隐私保护的良好平衡。
原文摘要 · Abstract (English)
We introduce $Urania$, a novel framework for generating insights about LLM chatbot interactions with rigorous differential privacy (DP) guarantees. The framework employs a private clustering mechanism and innovative keyword extraction methods, including frequency-based, TF-IDF-based, and LLM-guided approaches. By leveraging DP tools such as clustering, partition selection, and histogram-based summarization, $Urania$ provides end-to-end privacy protection. Our evaluation assesses lexical and semantic content preservation, pair similarity, and LLM-based metrics, benchmarking against a non-private Clio-inspired pipeline (Tamkin et al., 2024). Moreover, we develop a simple empirical privacy evaluation that demonstrates the enhanced robustness of our DP pipeline. The results show the framework's ability to extract meaningful conversational insights while maintaining stringent user privacy, effectively balancing data utility with privacy preservation.
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。