Showing 2026Show all
2 papers · 1 filter
cs.CR2026
Toward provably private learning from federated data
Katharine Daly, Yu Xiao, Zachary Garrett +9
Federated Learning (FL) allows devices with private data to collaborate in training a shared model. We present a next-generation FL system based on Trusted Execution Environments (…
cs.LG2026
Advancing the State-of-the-Art in Empirical Privacy Auditing
Nicole Mitchell, Galen Andrew, Arun Ganesh +2
Parameter-efficient fine-tuning of large language models (LLMs) can exhibit problematic memorization of individual training examples. Empirical privacy auditing (EPA) quantifies th…