Abstract Machine Learning (ML) models are ubiquitous in real-world applications and are a
constant focus of research. Modern ML models have become more complex, deeper, and …

We give simpler, sparser, and faster algorithms for differentially private fine-tuning of large-
scale pre-trained language models, which achieve the state-of-the-art privacy versus utility …

A key tool for building differentially private systems is adding Gaussian noise to the output of
a function evaluated on a sensitive dataset. Unfortunately, using a continuous distribution …

We give a fast algorithm to compose privacy guarantees of differentially private (DP)
algorithms to arbitrary accuracy. Our method is based on the notion of privacy loss random …

Differentially private (DP) machine learning allows us to train models on private data while
limiting data leakage. DP formalizes this data leakage through a cryptographic game, where …

Characterizing the privacy degradation over compositions, ie, privacy accounting, is a
fundamental topic in differential privacy (DP) with many applications to differentially private …

Internet banking security is one of the main critical issues among online users over the
world. High level of threats, lack of trust, and fear of loss are the main barriers to utilize …

This chapter is meant to be part of the book" Differential Privacy for Artificial Intelligence
Applications." We give an introduction to the most important property of differential privacy …

We investigate practical and scalable algorithms for training large language models (LLMs)
with user-level differential privacy (DP) in order to provably safeguard all the examples …

Motivated by recent applications requiring differential privacy in the setting of adaptive
streams, we investigate the question of optimal instantiations of the matrix mechanism in this …