Jump to Content
Aaron Segal

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.
Authored Publications
Google Publications
Other Publications
Sort By
  • Title
  • Title, desc
  • Year
  • Year, desc
    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