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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

There has been recent interest in leveraging federated learning (FL) forradio signal classification tasks. In FL, model parameters are periodicallycommunicated from participating devices, training on their own local datasets,to a central server which aggregates them into a global model. While FL hasprivacy/security advantages due to raw data not leaving the devices, it isstill susceptible to several adversarial attacks. In this work, we reveal thesusceptibility of FL-based signal classifiers to model poisoning attacks, whichcompromise the training process despite not observing data transmissions. Inthis capacity, we develop an attack framework in which compromised FL devicesperturb their local datasets using adversarial evasion attacks. As a result,the training process of the global model significantly degrades onin-distribution signals (i.e., signals received over channels with identicaldistributions at each edge device). We compare our work to previously proposedFL attacks and reveal that as few as one adversarial device operating with alow-powered perturbation under our attack framework can induce the potent modelpoisoning attack to the global classifier. Moreover, we find that more devicespartaking in adversarial poisoning will proportionally degrade theclassification performance.

How Potent are Evasion Attacks for Poisoning Federated Learning-Based Signal Classifiers?