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 Privacy-Preserving Neural Network (HPPNN) implementing linear layersby Homomorphic Encryption (HE) and nonlinear layers by Garbled Circuit (GC) isone of the most promising secure solutions to emerging Machine Learning as aService (MLaaS). Unfortunately, a HPPNN suffers from long inference latency,e.g., $\sim100$ seconds per image, which makes MLaaS unsatisfactory. BecauseHE-based linear layers of a HPPNN cost $93\%$ inference latency, it is criticalto select a set of HE parameters to minimize computational overhead of linearlayers. Prior HPPNNs over-pessimistically select huge HE parameters to maintainlarge noise budgets, since they use the same set of HE parameters for an entirenetwork and ignore the error tolerance capability of a network.  In this paper, for fast and accurate secure neural network inference, wepropose an automated layer-wise parameter selector, AutoPrivacy, that leveragesdeep reinforcement learning to automatically determine a set of HE parametersfor each linear layer in a HPPNN. The learning-based HE parameter selectionpolicy outperforms conventional rule-based HE parameter selection policy.Compared to prior HPPNNs, AutoPrivacy-optimized HPPNNs reduce inference latencyby $53\%\sim70\%$ with negligible loss of accuracy.

AutoPrivacy: Automated Layer-wise Parameter Selection for Secure Neural Network Inference