Differentially private image classification by learning priors from random processes
In privacy-preserving machine learning, differentially private stochastic gradient descent (DP-
SGD) performs worse than SGD due to per-sample gradient clipping and noise addition. A …
SGD) performs worse than SGD due to per-sample gradient clipping and noise addition. A …
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 …
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 …
Banded square root matrix factorization for differentially private model training
NP Kalinin, C Lampert - arXiv preprint arXiv:2405.13763, 2024 - arxiv.org
Current state-of-the-art methods for differentially private model training are based on matrix
factorization techniques. However, these methods suffer from high computational overhead …
factorization techniques. However, these methods suffer from high computational overhead …
Near exact privacy amplification for matrix mechanisms
CA Choquette-Choo, A Ganesh, S Haque… - arXiv preprint arXiv …, 2024 - arxiv.org
We study the problem of computing the privacy parameters for DP machine learning when
using privacy amplification via random batching and noise correlated across rounds via a …
using privacy amplification via random batching and noise correlated across rounds via a …
Doppler: Differentially private optimizers with low-pass filter for privacy noise reduction
Privacy is a growing concern in modern deep-learning systems and applications.
Differentially private (DP) training prevents the leakage of sensitive information in the …
Differentially private (DP) training prevents the leakage of sensitive information in the …
Correlated Privacy Mechanisms for Differentially Private Distributed Mean Estimation
Differentially private distributed mean estimation (DP-DME) is a fundamental building block
in privacy-preserving federated learning, where a central server estimates the mean of $ d …
in privacy-preserving federated learning, where a central server estimates the mean of $ d …
Improved Communication-Privacy Trade-offs in Mean Estimation under Streaming Differential Privacy
We study $ L_2 $ mean estimation under central differential privacy and communication
constraints, and address two key challenges: firstly, existing mean estimation schemes that …
constraints, and address two key challenges: firstly, existing mean estimation schemes that …
Secure Stateful Aggregation: A Practical Protocol with Applications in Differentially-Private Federated Learning
Recent advances in differentially private federated learning (DPFL) algorithms have found
that using correlated noise across the rounds of federated learning (DP-FTRL) yields …
that using correlated noise across the rounds of federated learning (DP-FTRL) yields …
Optimal Rates for DP-SCO with a Single Epoch and Large Batches
The most common algorithms for differentially private (DP) machine learning (ML) are all
based on stochastic gradient descent, for example, DP-SGD. These algorithms achieve DP …
based on stochastic gradient descent, for example, DP-SGD. These algorithms achieve DP …