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 adoption of machine learning solutions is rapidly increasing across allparts of society. Cloud service providers such as Amazon Web Services,Microsoft Azure and the Google Cloud Platform aggressively expand theirMachine-Learning-as-a-Service offerings. While the widespread adoption ofmachine learning has huge potential for both research and industry, thelarge-scale evaluation of possibly sensitive data on untrusted platforms bearsinherent data security and privacy risks. Since computation time is expensive,performance is a critical factor for machine learning. However, prevailingsecurity measures proposed in the past years come with a significantperformance overhead. We investigate the current state of protected distributedmachine learning systems, focusing on deep convolutional neural networks. Themost common and best-performing mixed MPC approaches are based on homomorphicencryption, secret sharing, and garbled circuits. They commonly suffer fromcommunication overheads that grow linearly in the depth of the neural network.We present Dash, a fast and distributed private machine learning inferencescheme. Dash is based purely on arithmetic garbled circuits. It requires only asingle communication round per inference step, regardless of the depth of theneural network, and a very small constant communication volume. Dash thussignificantly reduces performance requirements and scales better than previousapproaches. In addition, we introduce the concept of LabelTensors. This allowsus to efficiently use GPUs while using garbled circuits, which further reducesthe runtime. Dash offers security against a malicious attacker and is up to 140times faster than previous arithmetic garbling schemes.

DASH: Accelerating Distributed Private Machine Learning Inference with Arithmetic Garbled Circuits