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

This paper proposes a novel, data-agnostic, model poisoning attack onFederated Learning (FL), by designing a new adversarial graph autoencoder(GAE)-based framework. The attack requires no knowledge of FL training data andachieves both effectiveness and undetectability. By listening to the benignlocal models and the global model, the attacker extracts the graph structuralcorrelations among the benign local models and the training data featuressubstantiating the models. The attacker then adversarially regenerates thegraph structural correlations while maximizing the FL training loss, andsubsequently generates malicious local models using the adversarial graphstructure and the training data features of the benign ones. A new algorithm isdesigned to iteratively train the malicious local models using GAE andsub-gradient descent. The convergence of FL under attack is rigorously proved,with a considerably large optimality gap. Experiments show that the FL accuracydrops gradually under the proposed attack and existing defense mechanisms failto detect it. The attack can give rise to an infection across all benigndevices, making it a serious threat to FL.

Data-Agnostic Model Poisoning against Federated Learning: A Graph Autoencoder Approach