Practical Secure Aggregation for Federated Learning on User-Held Data
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.
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.
Research Areas
