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

Decentralized federated learning (DFL) is an effective approach to train adeep learning model at multiple nodes over a multi-hop network, without theneed of a server having direct connections to all nodes. In general, as long asnodes are connected potentially via multiple hops, the DFL process willeventually allow each node to experience the effects of models from all othernodes via either direct connections or multi-hop paths, and thus is able totrain a high-fidelity model at each node. We consider an effective attack thatuses jammers to prevent the model exchanges between nodes. There are two attackscenarios. First, the adversary can attack any link under a certain budget.Once attacked, two end nodes of a link cannot exchange their models. Secondly,some jammers with limited jamming ranges are deployed in the network and ajammer can only jam nodes within its jamming range. Once a directional link isattacked, the receiver node cannot receive the model from the transmitter node.We design algorithms to select links to be attacked for both scenarios. For thesecond scenario, we also design algorithms to deploy jammers at optimallocations so that they can attack critical nodes and achieve the highest impacton the DFL process. We evaluate these algorithms by using wireless signalclassification over a large network area as the use case and identify how theseattack mechanisms exploits various learning, connectivity, and sensing aspects.We show that the DFL performance can be significantly reduced by jammingattacks launched in a wireless network and characterize the attack surface as avulnerability study before the safe deployment of DFL over wireless networks.

Jamming Attacks on Decentralized Federated Learning in General Multi-Hop Wireless Networks