In the past decade, differential privacy has seen remarkable success as a rigorous and
practical formalization of data privacy. This privacy definition and its divergence based …

Recent developments in deep learning have led to great success in various natural
language processing (NLP) tasks. However, these applications may involve data that …

Motivated by the security risks of deep neural networks, such as various membership and
attribute inference attacks, differential privacy has emerged as a promising approach for …

Federated learning (FL) is a training paradigm where the clients collaboratively learn
models by repeatedly sharing information without compromising much on the privacy of their …

Differentially private (DP) machine learning algorithms incur many sources of randomness,
such as random initialization, random batch subsampling, and shuffling. However, such …

Privacy and Byzantine resilience are two indispensable requirements for a federated
learning (FL) system. Although there have been extensive studies on privacy and Byzantine …

Many modern machine learning algorithms are composed of simple private algorithms; thus,
an increasingly important problem is to efficiently compute the overall privacy loss under …

Differentially private mechanisms restrict the membership inference capabilities of powerful
(optimal) adversaries against machine learning models. Such adversaries are rarely …

This paper considers the problem of differentially private vertically partitioned data sharing.
In particular, with the assistance of a semi-honest curator, the involved parties (ie, data …

Differential privacy (DP) is a widely used approach for mitigating privacy risks when training
machine learning models on sensitive data. DP mechanisms add noise during training to …