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 (FL) allows participants to collaboratively train machineand deep learning models while protecting data privacy. However, the FLparadigm still presents drawbacks affecting its trustworthiness since maliciousparticipants could launch adversarial attacks against the training process.Related work has studied the robustness of horizontal FL scenarios underdifferent attacks. However, there is a lack of work evaluating the robustnessof decentralized vertical FL and comparing it with horizontal FL architecturesaffected by adversarial attacks. Thus, this work proposes three decentralizedFL architectures, one for horizontal and two for vertical scenarios, namelyHoriChain, VertiChain, and VertiComb. These architectures present differentneural networks and training protocols suitable for horizontal and verticalscenarios. Then, a decentralized, privacy-preserving, and federated use casewith non-IID data to classify handwritten digits is deployed to evaluate theperformance of the three architectures. Finally, a set of experiments computesand compares the robustness of the proposed architectures when they areaffected by different data poisoning based on image watermarks and gradientpoisoning adversarial attacks. The experiments show that even though particularconfigurations of both attacks can destroy the classification performance ofthe architectures, HoriChain is the most robust one.

Analyzing the Robustness of Decentralized Horizontal and Vertical Federated Learning Architectures in a Non-IID Scenario