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

Implementations of SGD on distributed systems create new vulnerabilities,which can be identified and misused by one or more adversarial agents.Recently, it has been shown that well-known Byzantine-resilient gradientaggregation schemes are indeed vulnerable to informed attackers that can tailorthe attacks (Fang et al., 2020; Xie et al., 2020b). We introduce MixTailor, ascheme based on randomization of the aggregation strategies that makes itimpossible for the attacker to be fully informed. Deterministic schemes can beintegrated into MixTailor on the fly without introducing any additionalhyperparameters. Randomization decreases the capability of a powerful adversaryto tailor its attacks, while the resulting randomized aggregation scheme isstill competitive in terms of performance. For both iid and non-iid settings,we establish almost sure convergence guarantees that are both stronger and moregeneral than those available in the literature. Our empirical studies acrossvarious datasets, attacks, and settings, validate our hypothesis and show thatMixTailor successfully defends when well-known Byzantine-tolerant schemes fail.

MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attacks