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

Federated learning enables collaborative training of machine learning modelsby keeping the raw data of the involved workers private. One of its mainobjectives is to improve the models' privacy, security, and scalability.Vertical Federated Learning (VFL) offers an efficient cross-silo setting wherea few parties collaboratively train a model without sharing the same features.In such a scenario, classification labels are commonly considered sensitiveinformation held exclusively by one (active) party, while other (passive)parties use only their local information. Recent works have uncovered importantflaws of VFL, leading to possible label inference attacks under the assumptionthat the attacker has some, even limited, background knowledge on the relationbetween labels and data. In this work, we are the first (to the best of ourknowledge) to investigate label inference attacks on VFL using azero-background knowledge strategy. To concretely formulate our proposal, wefocus on Graph Neural Networks (GNNs) as a target model for the underlying VFL.In particular, we refer to node classification tasks, which are widely studied,and GNNs have shown promising results. Our proposed attack, BlindSage, providesimpressive results in the experiments, achieving nearly 100% accuracy in mostcases. Even when the attacker has no information about the used architecture orthe number of classes, the accuracy remained above 85% in most instances.Finally, we observe that well-known defenses cannot mitigate our attack withoutaffecting the model's performance on the main classification task.

BlindSage: Label Inference Attacks against Node-level Vertical Federated Graph Neural Networks