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

Federated learning is an emerging data-private distributed learningframework, which, however, is vulnerable to adversarial attacks. Althoughseveral heuristic defenses are proposed to enhance the robustness of federatedlearning, they do not provide certifiable robustness guarantees. In this paper,we incorporate randomized smoothing techniques into federated adversarialtraining to enable data-private distributed learning with certifiablerobustness to test-time adversarial perturbations. Our experiments show thatsuch an advanced federated adversarial learning framework can deliver models asrobust as those trained by the centralized training. Further, this enablesprovably-robust classifiers to $\ell_2$-bounded adversarial perturbations in adistributed setup. We also show that one-point gradient estimation basedtraining approach is $2-3\times$ faster than popular stochastic estimator basedapproach without any noticeable certified robustness differences.

Certifiably-Robust Federated Adversarial Learning via Randomized Smoothing