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

For model privacy, local model parameters in federated learning shall beobfuscated before sent to the remote aggregator. This technique is referred toas \emph{secure aggregation}. However, secure aggregation makes model poisoningattacks such backdooring more convenient considering that existing anomalydetection methods mostly require access to plaintext local models. This paperproposes SAFELearning which supports backdoor detection for secure aggregation.We achieve this through two new primitives - \emph{oblivious random grouping(ORG)} and \emph{partial parameter disclosure (PPD)}. ORG partitionsparticipants into one-time random subgroups with group configurations obliviousto participants; PPD allows secure partial disclosure of aggregated subgroupmodels for anomaly detection without leaking individual model privacy.SAFELearning can significantly reduce backdoor model accuracy withoutjeopardizing the main task accuracy under common backdoor strategies. Extensiveexperiments show SAFELearning is robust against malicious and faultyparticipants, whilst being more efficient than the state-of-art secureaggregation protocol in terms of both communication and computation costs.

SAFELearning: Enable Backdoor Detectability In Federated Learning With Secure Aggregation