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 …

Traditional deep learning models are trained at a centralized server using data samples
collected from users. Such data samples often include private information, which the users …

Many machine learning tasks involve learning functions that are known to be invariant or
equivariant to certain symmetries of the input data. However, it is often challenging to design …

This paper discusses the contemporary problem of providing multiple-access (MAC) to a
massive number of uncoordinated users. First, we define a random-access code for K a-user …

We derive upper bounds on the generalization error of a learning algorithm in terms of the
mutual information between its input and output. The bounds provide an information …

The last years have witnessed the emergence of a promising self-supervised learning
strategy, referred to as masked autoencoding. However, there is a lack of theoretical …

Inference capabilities of machine learning (ML) systems skyrocketed in recent years, now
playing a pivotal role in various aspect of society. The goal in statistical learning is to use …

Consider a stochastic process being controlled across a communication channel. The
control signal that is transmitted across the control channel can be replaced by a malicious …

Recent work of Li and Micciancio (Eurocrypt 2021) has shown that the traditional formulation
of indistinguishability under chosen plaintext attack (IND-CPA) is not adequate to capture …

The quality of signal propagation in message-passing graph neural networks (GNNs)
strongly influences their expressivity as has been observed in recent works. In particular, for …