Splintering with distributions: A stochastic decoy scheme for private computation
Performing computations while maintaining privacy is an important problem in todays
distributed machine learning solutions. Consider the following two set ups between a client …
distributed machine learning solutions. Consider the following two set ups between a client …
[PDF][PDF] Splintering with distributions and polytopes: Unconventional schemes for private computation
Performing computations while maintaining privacy is an important problem in todays
distributed machine learning solutions. Consider the following two set ups between a client …
distributed machine learning solutions. Consider the following two set ups between a client …
Privacy amplification via bernoulli sampling
J Imola, K Chaudhuri - arXiv preprint arXiv:2105.10594, 2021 - arxiv.org
Balancing privacy and accuracy is a major challenge in designing differentially private
machine learning algorithms. One way to improve this tradeoff for free is to leverage the …
machine learning algorithms. One way to improve this tradeoff for free is to leverage the …
Almost tight error bounds on differentially private continual counting
The first large-scale deployment of private federated learning uses differentially private
counting in the continual release model as a subroutine (Google AI blog titled “Federated …
counting in the continual release model as a subroutine (Google AI blog titled “Federated …
Differential secrecy for distributed data and applications to robust differentially secure vector summation
K Talwar - arXiv preprint arXiv:2202.10618, 2022 - arxiv.org
Computing the noisy sum of real-valued vectors is an important primitive in differentially
private learning and statistics. In private federated learning applications, these vectors are …
private learning and statistics. In private federated learning applications, these vectors are …
Private inference in quantized models
A typical setup in many machine learning scenarios involves a server that holds a model
and a user that possesses data, and the challenge is to perform inference while …
and a user that possesses data, and the challenge is to perform inference while …
Algorithmically effective differentially private synthetic data
We present a highly effective algorithmic approach for generating $\varepsilon $-
differentially private synthetic data in a bounded metric space with near-optimal utility …
differentially private synthetic data in a bounded metric space with near-optimal utility …
Poission subsampled rényi differential privacy
We consider the problem of privacy-amplification by under the Renyi Differential Privacy
framework. This is the main technique underlying the moments accountants (Abadi et al …
framework. This is the main technique underlying the moments accountants (Abadi et al …
A decentralized and robust protocol for private averaging over highly distributed data
We propose a decentralized protocol for a large set of users to privately compute averages
over their joint data, which can later be used to learn more complex models. Our protocol …
over their joint data, which can later be used to learn more complex models. Our protocol …
A practical scheme for two-party private linear least squares
M Nassar - arXiv preprint arXiv:1901.09281, 2019 - arxiv.org
Privacy-preserving machine learning is learning from sensitive datasets that are typically
distributed across multiple data owners. Private machine learning is a remarkable challenge …
distributed across multiple data owners. Private machine learning is a remarkable challenge …