Privacy-preserving distributed learning in the analog domain
We consider the critical problem of distributed learning over data while keeping it private
from the computational servers. The state-of-the-art approaches to this problem rely on …
from the computational servers. The state-of-the-art approaches to this problem rely on …
Analog secret sharing with applications to private distributed learning
M Soleymani, H Mahdavifar… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
We consider the critical problems of distributed computing and learning over data while
keeping it private from the computational servers. The state-of-the-art approaches to this …
keeping it private from the computational servers. The state-of-the-art approaches to this …
CodedPrivateML: A fast and privacy-preserving framework for distributed machine learning
How to train a machine learning model while keeping the data private and secure? We
present CodedPrivateML, a fast and scalable approach to this critical problem …
present CodedPrivateML, a fast and scalable approach to this critical problem …
Breaking the communication-privacy-accuracy trilemma
Two major challenges in distributed learning and estimation are 1) preserving the privacy of
the local samples; and 2) communicating them efficiently to a central server, while achieving …
the local samples; and 2) communicating them efficiently to a central server, while achieving …
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 …
Breaking the communication-privacy-accuracy trilemma
Two major challenges in distributed learning and estimation are 1) preserving the privacy of
the local samples; and 2) communicating them efficiently to a central server, while achieving …
the local samples; and 2) communicating them efficiently to a central server, while achieving …
Layered Randomized Quantization for Communication-Efficient and Privacy-Preserving Distributed Learning
Next-generation wireless networks, such as edge intelligence and wireless distributed
learning, face two critical challenges: communication efficiency and privacy protection. In …
learning, face two critical challenges: communication efficiency and privacy protection. In …
Differentially private cross-silo federated learning
Strict privacy is of paramount importance in distributed machine learning. Federated
learning, with the main idea of communicating only what is needed for learning, has been …
learning, with the main idea of communicating only what is needed for learning, has been …
Distributed learning without distress: Privacy-preserving empirical risk minimization
Distributed learning allows a group of independent data owners to collaboratively learn a
model over their data sets without exposing their private data. We present a distributed …
model over their data sets without exposing their private data. We present a distributed …
Differentially private distributed online learning
In the big data era, the generation of data presents some new characteristics, including wide
distribution, high velocity, high dimensionality, and privacy concern. To address these …
distribution, high velocity, high dimensionality, and privacy concern. To address these …