Samplable anonymous aggregation for private federated data analysis
We revisit the problem of designing scalable protocols for private statistics and private
federated learning when each device holds its private data. Our first contribution is to …
federated learning when each device holds its private data. Our first contribution is to …
Private federated statistics in an interactive setting
A McMillan, O Javidbakht, K Talwar, E Briggs… - arXiv preprint arXiv …, 2022 - arxiv.org
Privately learning statistics of events on devices can enable improved user experience.
Differentially private algorithms for such problems can benefit significantly from interactivity …
Differentially private algorithms for such problems can benefit significantly from interactivity …
An accurate, scalable and verifiable protocol for federated differentially private averaging
Learning from data owned by several parties, as in federated learning, raises challenges
regarding the privacy guarantees provided to participants and the correctness of the …
regarding the privacy guarantees provided to participants and the correctness of the …
Scalable and differentially private distributed aggregation in the shuffled model
Federated learning promises to make machine learning feasible on distributed, private
datasets by implementing gradient descent using secure aggregation methods. The idea is …
datasets by implementing gradient descent using secure aggregation methods. The idea is …
The fundamental price of secure aggregation in differentially private federated learning
We consider the problem of training a $ d $ dimensional model with distributed differential
privacy (DP) where secure aggregation (SecAgg) is used to ensure that the server only sees …
privacy (DP) where secure aggregation (SecAgg) is used to ensure that the server only sees …
Efficient differentially private secure aggregation for federated learning via hardness of learning with errors
Federated machine learning leverages edge computing to develop models from network
user data, but privacy in federated learning remains a major challenge. Techniques using …
user data, but privacy in federated learning remains a major challenge. Techniques using …
The distributed discrete gaussian mechanism for federated learning with secure aggregation
We consider training models on private data that are distributed across user devices. To
ensure privacy, we add on-device noise and use secure aggregation so that only the noisy …
ensure privacy, we add on-device noise and use secure aggregation so that only the noisy …
[PDF][PDF] Federated learning and privacy
Federated learning and privacy Page 1 90 COMMUNICATIONS OF THE ACM | APRIL 2022 |
VOL. 65 | NO. 4 practice DOI:10.1145/3500240 Article development led by queue.acm.org …
VOL. 65 | NO. 4 practice DOI:10.1145/3500240 Article development led by queue.acm.org …
The skellam mechanism for differentially private federated learning
We introduce the multi-dimensional Skellam mechanism, a discrete differential privacy
mechanism based on the difference of two independent Poisson random variables. To …
mechanism based on the difference of two independent Poisson random variables. To …
Distributed differentially private averaging with improved utility and robustness to malicious parties
Learning from data owned by several parties, as in federated learning, raises challenges
regarding the privacy guarantees provided to participants and the correctness of the …
regarding the privacy guarantees provided to participants and the correctness of the …