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

In vertical federated learning (VFL), commercial entities collaborativelytrain a model while preserving data privacy. However, a malicious participant'spoisoning attack may degrade the performance of this collaborative model. Themain challenge in achieving the poisoning attack is the absence of access tothe server-side top model, leaving the malicious participant without a cleartarget model. To address this challenge, we introduce an innovative end-to-endpoisoning framework P-GAN. Specifically, the malicious participant initiallyemploys semi-supervised learning to train a surrogate target model.Subsequently, this participant employs a GAN-based method to produceadversarial perturbations to degrade the surrogate target model's performance.Finally, the generator is obtained and tailored for VFL poisoning. Besides, wedevelop an anomaly detection algorithm based on a deep auto-encoder (DAE),offering a robust defense mechanism to VFL scenarios. Through extensiveexperiments, we evaluate the efficacy of P-GAN and DAE, and further analyze thefactors that influence their performance.

A GAN-based data poisoning framework against anomaly detection in vertical federated learning