Скачать или смотреть PEPR '25 - When Privacy Guarantees Meet Pre-Trained LLMs: A Case Study in Synthetic Data

When Privacy Guarantees Meet Pre-Trained LLMs: A Case Study in Synthetic Data

Yash Maurya and Aman Priyanshu, Carnegie Mellon University

Modern synthetic data generation with privacy guarantees has become increasingly prevalent. Take real data, create synthetic versions following similar patterns, and ensure privacy through differential privacy mechanisms. But what happens when theoretical privacy guarantees meet real-world data? Even with conservative epsilon values (ε less than10), document formatting and contextual patterns can create unexpected privacy challenges, especially when using models which aren't transparent about their own training data like most LLMs.

View the full PEPR 25 program at https://www.usenix.org/conference/pep...