Pre-training on public data is an effective method to improve the performance for federated
learning (FL) with differential privacy (DP). This paper investigates how large language …

Large Language Models (LLMs) achieve state-of-the-art performance but are challenging to
deploy due to their high computational and storage demands. Pruning can reduce model …

Substantial quantity and high quality are the golden rules of making a good training dataset
with sample privacy protection equally important. Generating synthetic samples that …

Initializing with pre-trained models when learning on downstream tasks is becoming
standard practice in machine learning. Several recent works explore the benefits of pre …

Differentially private (DP) synthetic data, which closely resembles the original private data
while maintaining strong privacy guarantees, has become a key tool for unlocking the value …

Federated Learning (FL) is a collaborative, privacy-preserving machine learning framework
that enables multiple participants to train a single global model. However, the recent advent …

Differentially private (DP) synthetic data is a versatile tool for enabling the analysis of private
data. Recent advancements in large language models (LLMs) have inspired a number of …

Abstract Machine learning (ML) generally performs well when there is unfettered access to
large quantities of clean, relevant data. However, harnessing the benefits of large, clean …

Abstract Machine learning models are susceptible to a range of attacks that exploit data
leakage from trained models. Differential Privacy (DP) is the gold standard for quantifying …