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

With the advancement of machine learning (ML) and its growing awareness, manyorganizations who own data but not ML expertise (data owner) would like to pooltheir data and collaborate with those who have expertise but need data fromdiverse sources to train truly generalizable models (model owner). In suchcollaborative ML, the data owner wants to protect the privacy of its trainingdata, while the model owner desires the confidentiality of the model and thetraining method which may contain intellectual properties. However, existingprivate ML solutions, such as federated learning and split learning, cannotmeet the privacy requirements of both data and model owners at the same time.  This paper presents Citadel, a scalable collaborative ML system that protectsthe privacy of both data owner and model owner in untrusted infrastructureswith the help of Intel SGX. Citadel performs distributed training acrossmultiple training enclaves running on behalf of data owners and an aggregatorenclave on behalf of the model owner. Citadel further establishes a stronginformation barrier between these enclaves by means of zero-sum masking andhierarchical aggregation to prevent data/model leakage during collaborativetraining. Compared with the existing SGX-protected training systems, Citadelenables better scalability and stronger privacy guarantees for collaborativeML. Cloud deployment with various ML models shows that Citadel scales to alarge number of enclaves with less than 1.73X slowdown caused by SGX.

Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning with SGX