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 paradigm in Machine Learning (ML) that addressesdata privacy, security, access rights and access to heterogeneous informationissues by training a global model using distributed nodes. Despite itsadvantages, there is an increased potential for cyberattacks on FL-based MLtechniques that can undermine the benefits. Model-poisoning attacks on FLtarget the availability of the model. The adversarial objective is to disruptthe training. We propose attestedFL, a defense mechanism that monitors thetraining of individual nodes through state persistence in order to detect amalicious worker. A fine-grained assessment of the history of the workerpermits the evaluation of its behavior in time and results in innovativedetection strategies. We present three lines of defense that aim at assessingif the worker is reliable by observing if the node is really training,advancing towards a goal. Our defense exposes an attacker's malicious behaviorand removes unreliable nodes from the aggregation process so that the FLprocess converge faster. Through extensive evaluations and against variousadversarial settings, attestedFL increased the accuracy of the model between12% to 58% under different scenarios such as attacks performed at differentstages of convergence, attackers colluding and continuous attacks.

Untargeted Poisoning Attack Detection in Federated Learning via Behavior Attestation