Multi-epoch matrix factorization mechanisms for private machine learning
We introduce new differentially private (DP) mechanisms for gradient-based machine
learning (ML) with multiple passes (epochs) over a dataset, substantially improving the …
learning (ML) with multiple passes (epochs) over a dataset, substantially improving the …
Constant matters: Fine-grained error bound on differentially private continual observation
H Fichtenberger, M Henzinger… - … on Machine Learning, 2023 - proceedings.mlr.press
We study fine-grained error bounds for differentially private algorithms for counting under
continual observation. Our main insight is that the matrix mechanism when using lower …
continual observation. Our main insight is that the matrix mechanism when using lower …
A unifying framework for differentially private sums under continual observation
We study the problem of maintaining a differentially private decaying sum under continual
observation. We give a unifying framework and an efficient algorithm for this problem for any …
observation. We give a unifying framework and an efficient algorithm for this problem for any …
A smooth binary mechanism for efficient private continual observation
JD Andersson, R Pagh - Advances in Neural Information …, 2024 - proceedings.neurips.cc
In privacy under continual observation we study how to release differentially private
estimates based on a dataset that evolves over time. The problem of releasing private prefix …
estimates based on a dataset that evolves over time. The problem of releasing private prefix …
Continual observation under user-level differential privacy
In the foundational work of Dwork et al.[15] on continual observation under differential
privacy (DP), two privacy models have been proposed: event-level DP and user-level DP …
privacy (DP), two privacy models have been proposed: event-level DP and user-level DP …
Efficient and near-optimal noise generation for streaming differential privacy
In the task of differentially private (DP) continual counting, we receive a stream of increments
and our goal is to output an approximate running total of these increments, without revealing …
and our goal is to output an approximate running total of these increments, without revealing …
The discrepancy of shortest paths
The hereditary discrepancy of a set system is a certain quantitative measure of the
pseudorandom properties of the system. Roughly, hereditary discrepancy measures how …
pseudorandom properties of the system. Roughly, hereditary discrepancy measures how …
Concurrent shuffle differential privacy under continual observation
We introduce the concurrent shuffle model of differential privacy. In this model we have
multiple concurrent shufflers permuting messages from different, possibly overlapping …
multiple concurrent shufflers permuting messages from different, possibly overlapping …
On differentially private counting on trees
We study the problem of performing counting queries at different levels in hierarchical
structures while preserving individuals' privacy. Motivated by applications, we propose a …
structures while preserving individuals' privacy. Motivated by applications, we propose a …
Continual Observation of Joins under Differential Privacy
The problem of continual observation under differential privacy has been studied extensively
in the literature. However, all existing works, with the exception of [28, 51], have only studied …
in the literature. However, all existing works, with the exception of [28, 51], have only studied …