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

Secure multi-party computation (MPC) allows users to offload machine learninginference on untrusted servers without having to share their privacy-sensitivedata. Despite their strong security properties, MPC-based private inference hasnot been widely adopted in the real world due to their high communicationoverhead. When evaluating ReLU layers, MPC protocols incur a significant amountof communication between the parties, making the end-to-end execution timemultiple orders slower than its non-private counterpart.  This paper presents HummingBird, an MPC framework that reduces the ReLUcommunication overhead significantly by using only a subset of the bits toevaluate ReLU on a smaller ring. Based on theoretical analyses, HummingBirdidentifies bits in the secret share that are not crucial for accuracy andexcludes them during ReLU evaluation to reduce communication. With itsefficient search engine, HummingBird discards 87--91% of the bits during ReLUand still maintains high accuracy. On a real MPC setup involving multipleservers, HummingBird achieves on average 2.03--2.67x end-to-end speedup withoutintroducing any errors, and up to 8.64x average speedup when some amount ofaccuracy degradation can be tolerated, due to its up to 8.76x communicationreduction.

Approximating ReLU on a Reduced Ring for Efficient MPC-based Private Inference