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

Federated learning (FL) is a distributed machine learning approach wheremultiple clients collaboratively train a joint model without exchanging theirdata. Despite FL's unprecedented success in data privacy-preserving, itsvulnerability to free-rider attacks has attracted increasing attention.Existing defenses may be ineffective against highly camouflaged or highpercentages of free riders. To address these challenges, we reconsider thedefense from a novel perspective, i.e., model weight evolvingfrequency.Empirically, we gain a novel insight that during the FL's training,the model weight evolving frequency of free-riders and that of benign clientsare significantly different. Inspired by this insight, we propose a noveldefense method based on the model Weight Evolving Frequency, referred to asWEF-Defense.Specifically, we first collect the weight evolving frequency(defined as WEF-Matrix) during local training. For each client, it uploads thelocal model's WEF-Matrix to the server together with its model weight for eachiteration. The server then separates free-riders from benign clients based onthe difference in the WEF-Matrix. Finally, the server uses a personalizedapproach to provide different global models for corresponding clients.Comprehensive experiments conducted on five datasets and five modelsdemonstrate that WEF-Defense achieves better defense effectiveness than thestate-of-the-art baselines.

Rethinking the Defense Against Free-rider Attack From the Perspective of Model Weight Evolving Frequency