Secure multiparty aggregation with differential privacy: a comparative study

By Slawomir Goryczka, Li Xiong, Vaidy S. Sunderam. 2013

86 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Federated & Distributed Learning, Privacy & Security

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

In Federated & Distributed Learning

In Privacy & Security

Citations in the corpus

The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation (2021, background): “For instance, the majority of existing works ignore the finite precision and modular summation arithmetic associated with secure aggregation (Goryczka et al., 2013; Truex et al., 2019; Valovich & Alda, 2017).”
Scalable and Differentially Private Distributed Aggregation in the Shuffled Model (2019, methodology): “We use a technique from protocols for secure multi-party aggregation (see e.g. [11]): Ensure that individual numbers passed to the analyzer are fully random by adding random noise terms, but coordinate the noise such that all noise terms cancel, and the sum remain the same as the sum of the…”
Communication-Efficient Learning of Deep Networks from Decentralized Data (2016, background): “While federated learning offers many practical privacy benefits, providing stronger guarantees via differential privacy [14, 13, 1], secure multi-party computation [18], or their combination is an interesting direction for future work.”
A Comprehensive Comparison of Multiparty Secure Additions with Differential Privacy (2015, background): “A preliminary version of the manuscript has been published in [32].”
Efficient Differentially Private F0 Linear Sketching (2020, methodology): “We note that our sketch would also work in a model where vectors supplied by the users are combined using a black-box multi-party secure aggregation [21, 33].”
Computational Differential Privacy from Lattice-Based Cryptography (2017, background): “For a survey of the mechanisms given in [30] and [2], we refer to [19].”
Federated Learning of Deep Networks using Model Averaging (2016, methodology): “It is also possible to use secure multiparty computation to perform aggregation over multiple client updates, allowing local differential privacy to be achieved using much less random noise (Goryczka et al., 2013).”
Combining Differential Privacy and Secure Multiparty Computation (2015, unknown): “Differentially private data aggregation has received a lot of interest [13, 1, 19], but typically without employing SMC.”
Differentially private data aggregation with optimal utility (2014, background): “Existing solutions are tailored to individual datatypes and perturbation mechanisms [5–7,14,15,29,32,38,39].”