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

While being an effective framework of learning a shared model across multipleedge devices, federated learning (FL) is generally vulnerable to Byzantineattacks from adversarial edge devices. While existing works on FL mitigate suchcompromised devices by only aggregating a subset of the local models at theserver side, they still cannot successfully ignore the outliers due toimprecise scoring rule. In this paper, we propose an effective Byzantine-robustFL framework, namely dummy contrastive aggregation, by defining a novel scoringfunction that sensitively discriminates whether the model has been poisoned ornot. Key idea is to extract essential information from every local models alongwith the previous global model to define a distance measure in a manner similarto triplet loss. Numerical results validate the advantage of the proposedapproach by showing improved performance as compared to the state-of-the-artByzantine-resilient aggregation methods, e.g., Krum, Trimmed-mean, and Fang.

Security-Preserving Federated Learning via Byzantine-Sensitive Triplet Distance