How to dp-fy ml: A practical guide to machine learning with differential privacy
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 …
constant focus of research. Modern ML models have become more complex, deeper, and …
A comprehensive survey of privacy-preserving federated learning: A taxonomy, review, and future directions
The past four years have witnessed the rapid development of federated learning (FL).
However, new privacy concerns have also emerged during the aggregation of the …
However, new privacy concerns have also emerged during the aggregation of the …
Advances and open problems in federated learning
Federated learning (FL) is a machine learning setting where many clients (eg, mobile
devices or whole organizations) collaboratively train a model under the orchestration of a …
devices or whole organizations) collaboratively train a model under the orchestration of a …
Differentially private learning with adaptive clipping
Existing approaches for training neural networks with user-level differential privacy (eg, DP
Federated Averaging) in federated learning (FL) settings involve bounding the contribution …
Federated Averaging) in federated learning (FL) settings involve bounding the contribution …
Privacy-preserving federated learning with malicious clients and honest-but-curious servers
Federated learning (FL) enables multiple clients to jointly train a global learning model while
keeping their training data locally, thereby protecting clients' privacy. However, there still …
keeping their training data locally, thereby protecting clients' privacy. However, there still …
Differentially private sql with bounded user contribution
RJ Wilson, CY Zhang, W Lam, D Desfontaines… - arXiv preprint arXiv …, 2019 - arxiv.org
Differential privacy (DP) provides formal guarantees that the output of a database query
does not reveal too much information about any individual present in the database. While …
does not reveal too much information about any individual present in the database. While …
Differential privacy and robust statistics in high dimensions
We introduce a universal framework for characterizing the statistical efficiency of a statistical
estimation problem with differential privacy guarantees. Our framework, which we call High …
estimation problem with differential privacy guarantees. Our framework, which we call High …
Learning with user-level privacy
We propose and analyze algorithms to solve a range of learning tasks under user-level
differential privacy constraints. Rather than guaranteeing only the privacy of individual …
differential privacy constraints. Rather than guaranteeing only the privacy of individual …
Learning to generate image embeddings with user-level differential privacy
Small on-device models have been successfully trained with user-level differential privacy
(DP) for next word prediction and image classification tasks in the past. However, existing …
(DP) for next word prediction and image classification tasks in the past. However, existing …
User-level differentially private learning via correlated sampling
Most works in learning with differential privacy (DP) have focused on the setting where each
user has a single sample. In this work, we consider the setting where each user holds $ m …
user has a single sample. In this work, we consider the setting where each user holds $ m …