Aaron Segal
PhD, Yale University 2016. Software engineer at Google NYC.
My main area of interest is cryptography, specifically secure multiparty computation and privacy-preserving protocols.
Research Areas
Authored Publications
Google Publications
Other Publications
Sort By
Practical Secure Aggregation for Privacy-Preserving Machine Learning
Antonio Marcedone
Benjamin Kreuter
Sarvar Patel
Vladimir Ivanov
CCS (2017)
Preview abstract
We design a novel, communication-efficient, failure-robust protocol for secure aggregation of high-dimensional data. Our protocol allows a server to collect an aggregate of user-held data from mobile devices in a privacy-preserving manner, and can be used, for example, in a federated learning setting, to aggregate user-provided model updates for a deep neural network. We prove the security of our protocol in the honest-but-curious and malicious server settings, and show that privacy is preserved even if an arbitrarily chosen subset of users drop out at any time. We evaluate the efficiency of our protocol and show, by complexity analysis and a concrete implementation, that its runtime and communication overhead remain low even on large data sets and client pools. For 16-bit input values, our protocol offers 1.73× communication expansion for 2^10 users and 2^20-dimensional vectors, and 1.98× expansion for 2^14 users and 2^24-dimensional vectors.
View details
Practical Secure Aggregation for Federated Learning on User-Held Data
Vladimir Ivanov
Ben Kreuter
Antonio Marcedone
Sarvar Patel
NIPS Workshop on Private Multi-Party Machine Learning (2016)
Preview abstract
Secure Aggregation is a class of Secure Multi-Party Computation algorithms wherein a group of
mutually distrustful parties u ∈ U each hold a private value x_u and collaborate to compute an
aggregate value, such as the sum_{u∈U} x_u, without revealing to one another any information about
their private value except what is learnable from the aggregate value itself. In this work, we consider
training a deep neural network in the Federated Learning model, using distributed gradient descent
across user-held training data on mobile devices, wherein Secure Aggregation protects the privacy of
each user’s model gradient. We identify a combination of efficiency and robustness requirements
which, to the best of our knowledge, are unmet by existing algorithms in the literature. We proceed to
design a novel, communication-efficient Secure Aggregation protocol for high-dimensional data that
tolerates up to 1/3 users failing to complete the protocol. For 16-bit input values, our protocol offers
1.73x communication expansion for 2^10 users and 2^20-dimensional vectors, and 1.98x expansion
for 2^14 users and 2^24 dimensional vectors.
View details
No Results Found
