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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Hybrid private inference (PI) protocol, which synergistically utilizes bothmulti-party computation (MPC) and homomorphic encryption, is one of the mostprominent techniques for PI. However, even the state-of-the-art PI protocolsare bottlenecked by the non-linear layers, especially the activation functions.Although a standard non-linear activation function can generate higher modelaccuracy, it must be processed via a costly garbled-circuit MPC primitive. Apolynomial activation can be processed via Beaver's multiplication triples MPCprimitive but has been incurring severe accuracy drops so far.  In this paper, we propose an accuracy preserving low-degree polynomialactivation function (AESPA) that exploits the Hermite expansion of the ReLU andbasis-wise normalization. We apply AESPA to popular ML models, such as VGGNet,ResNet, and pre-activation ResNet, to show an inference accuracy comparable tothose of the standard models with ReLU activation, achieving superior accuracyover prior low-degree polynomial studies. When applied to the all-RELU baselineon the state-of-the-art Delphi PI protocol, AESPA shows up to 42.1x and 28.3xlower online latency and communication cost.

AESPA: Accuracy Preserving Low-degree Polynomial Activation for Fast Private Inference