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

The proliferation of deep learning (DL) has led to the emergence of privacyand security concerns. To address these issues, secure Two-party computation(2PC) has been proposed as a means of enabling privacy-preserving DLcomputation. However, in practice, 2PC methods often incur high computation andcommunication overhead, which can impede their use in large-scale systems. Toaddress this challenge, we introduce RRNet, a systematic framework that aims tojointly reduce the overhead of MPC comparison protocols and acceleratecomputation through hardware acceleration. Our approach integrates the hardwarelatency of cryptographic building blocks into the DNN loss function, resultingin improved energy efficiency, accuracy, and security guarantees. Furthermore,we propose a cryptographic hardware scheduler and corresponding performancemodel for Field Programmable Gate Arrays (FPGAs) to further enhance theefficiency of our framework. Experiments show RRNet achieved a much higher ReLUreduction performance than all SOTA works on CIFAR-10 dataset.

RRNet: Towards ReLU-Reduced Neural Network for Two-party Computation Based Private Inference