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

Wireless ad hoc federated learning (WAFL) is a fully decentralizedcollaborative machine learning framework organized by opportunisticallyencountered mobile nodes. Compared to conventional federated learning, WAFLperforms model training by weakly synchronizing the model parameters withothers, and this shows great resilience to a poisoned model injected by anattacker. In this paper, we provide our theoretical analysis of the WAFL'sresilience against model poisoning attacks, by formulating the force balancebetween the poisoned model and the legitimate model. According to ourexperiments, we confirmed that the nodes directly encountered the attacker hasbeen somehow compromised to the poisoned model but other nodes have shown greatresilience. More importantly, after the attacker has left the network, all thenodes have finally found stronger model parameters combined with the poisonedmodel. Most of the attack-experienced cases achieved higher accuracy than theno-attack-experienced cases.

Resilience of Wireless Ad Hoc Federated Learning against Model Poisoning Attacks