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

Privacy and security concerns in real-world applications have led to thedevelopment of adversarially robust federated models. However, thestraightforward combination between adversarial training and federated learningin one framework can lead to the undesired robustness deterioration. Wediscover that the attribution behind this phenomenon is that the generatedadversarial data could exacerbate the data heterogeneity among local clients,making the wrapped federated learning perform poorly. To deal with thisproblem, we propose a novel framework called Slack Federated AdversarialTraining (SFAT), assigning the client-wise slack during aggregation to combatthe intensified heterogeneity. Theoretically, we analyze the convergence of theproposed method to properly relax the objective when combining federatedlearning and adversarial training. Experimentally, we verify the rationalityand effectiveness of SFAT on various benchmarked and real-world datasets withdifferent adversarial training and federated optimization methods. The code ispublicly available at https://github.com/ZFancy/SFAT.

Combating Exacerbated Heterogeneity for Robust Models in Federated Learning