Urania: Differentially Private Insights into AI Use

TL;DR

Urania is a new framework that provides privacy-preserving insights into AI chatbot interactions using differential privacy, innovative keyword extraction, and rigorous evaluation to balance data utility with user privacy.

Contribution

Urania introduces a comprehensive DP framework with novel keyword extraction and privacy evaluation methods for analyzing LLM interactions.

Findings

Effective preservation of lexical and semantic content.

Comparable insights to non-private pipelines.

Enhanced robustness in privacy guarantees.

Abstract

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.