English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The emerging applications of machine learning algorithms on mobile devicesmotivate us to offload the computation tasks of training a model or deploying atrained one to the cloud or at the edge of the network. One of the majorchallenges in this setup is to guarantee the privacy of the client data.Various methods have been proposed to protect privacy in the literature. Thoseinclude (i) adding noise to the client data, which reduces the accuracy of theresult, (ii) using secure multiparty computation (MPC), which requiressignificant communication among the computing nodes or with the client, (iii)relying on homomorphic encryption (HE) methods, which significantly increasescomputation load at the servers. In this paper, we propose $\textit{Corella}$as an alternative approach to protect the privacy of data. The proposed schemerelies on a cluster of servers, where at most $T \in \mathbb{N}$ of them maycollude, each running a learning model (e.g., a deep neural network). Eachserver is fed with the client data, added with $\textit{strong}$ noise,independent from user data. The variance of the noise is set to be large enoughto make the information leakage to any subset of up to $T$ serversinformation-theoretically negligible. On the other hand, the added noises fordifferent servers are $\textit{correlated}$. This correlation among the queriesallows the parameters of the models running on different servers to be$\textit{trained}$ such that the client can mitigate the contribution of thenoises by combining the outputs of the servers, and recover the final resultwith high accuracy and with a minor computational effort. Simulation resultsfor various datasets demonstrate the accuracy of the proposed approach for theclassification, using deep neural networks, and the autoencoder, as supervisedand unsupervised learning tasks, respectively.

Corella: A Private Multi Server Learning Approach based on Correlated Queries