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

Machine Learning as a Service (MLaaS) is enabling a wide range of smartapplications on end devices. However, such convenience comes with a cost ofprivacy because users have to upload their private data to the cloud. Thisresearch aims to provide effective and efficient MLaaS such that the cloudserver learns nothing about user data and the users cannot infer theproprietary model parameters owned by the server. This work makes the followingcontributions. First, it unveils the fundamental performance bottleneck ofexisting schemes due to the heavy permutations in computing lineartransformation and the use of communication intensive Garbled Circuits fornonlinear transformation. Second, it introduces an ultra-fast secure MLaaSframework, CHEETAH, which features a carefully crafted secret sharing schemethat runs significantly faster than existing schemes without accuracy loss.Third, CHEETAH is evaluated on the benchmark of well-known, practical deepnetworks such as AlexNet and VGG-16 on the MNIST and ImageNet datasets. Theresults demonstrate more than 100x speedup over the fastest GAZELLE (UsenixSecurity'18), 2000x speedup over MiniONN (ACM CCS'17) and five orders ofmagnitude speedup over CryptoNets (ICML'16). This significant speedup enables awide range of practical applications based on privacy-preserved deep neuralnetworks.

CHEETAH: An Ultra-Fast, Approximation-Free, and Privacy-Preserved Neural Network Framework based on Joint Obscure Linear and Nonlinear Computations