Urania: Differentially Private Insights into AI Use
This addresses privacy concerns for users of AI chatbots by providing a differentially private analysis method, though it builds incrementally on existing DP tools and clustering approaches.
The researchers tackled the problem of extracting insights from LLM chatbot interactions while protecting user privacy, introducing Urania, a differentially private framework that achieved meaningful conversational insights with rigorous privacy guarantees.
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.