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

Recently, Deep Convolutional Neural Networks (DCNNs) including the ResNet-20architecture have been privately evaluated on encrypted, low-resolution datawith the Residue-Number-System Cheon-Kim-Kim-Song (RNS-CKKS) homomorphicencryption scheme. We extend methods for evaluating DCNNs on images with largerdimensions and many channels, beyond what can be stored in single ciphertexts.Additionally, we simplify and improve the efficiency of the recently introducedmultiplexed image format, demonstrating that homomorphic evaluation can workwith standard, row-major matrix packing and results in encrypted inference timespeedups by $4.6-6.5\times$. We also show how existing DCNN models can beregularized during the training process to further improve efficiency andaccuracy. These techniques are applied to homomorphically evaluate a DCNN withhigh accuracy on the high-resolution ImageNet dataset for the first time,achieving $80.2\%$ top-1 accuracy. We also achieve the highest reportedaccuracy of homomorphically evaluated CNNs on the CIFAR-10 dataset of $98.3\%$.

High-Resolution Convolutional Neural Networks on Homomorphically Encrypted Data via Sharding Ciphertexts