Differential privacy is widely considered the formal privacy for privacy-preserving data
analysis due to its robust and rigorous guarantees, with increasingly broad adoption in …

We propose a simple heuristic privacy analysis of noisy clipped stochastic gradient descent
(DP-SGD) in the setting where only the last iterate is released and the intermediate iterates …

Federated learning (FL) is an efficient collaborative training paradigm extensively developed
with a focus on local privacy, and differential privacy (DP) is a classical approach to capture …

Coupling arguments are a central tool for bounding the deviation between two stochastic
processes, but traditionally have been limited to Wasserstein metrics. In this paper, we apply …

Auditing Differentially Private Stochastic Gradient Descent (DP-SGD) in the final model
setting is challenging and often results in empirical lower bounds that are significantly looser …

The US Decennial Census serves as the foundation for many high-profile policy decision-
making processes, including federal funding allocation and redistricting. In 2020, the …

The hidden state threat model of differential privacy (DP) assumes that the adversary has
access only to the final trained machine learning (ML) model, without seeing intermediate …

We propose a simple heuristic privacy analysis of noisy clipped stochastic gradient descent
(DP-SGD) in the setting where only the last iterate is released and the intermediate iterates …

A recent study by De et al.(2022) has reported that large-scale representation learning
through pre-training on a public dataset significantly enhances differentially private (DP) …

Differentially-private stochastic gradient descent (DP-SGD) is a family of iterative machine
learning training algorithms that privatize gradients to generate a sequence of differentially …