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 (FL) was originally regarded as a framework forcollaborative learning among clients with data privacy protection through acoordinating server. In this paper, we propose a new active membershipinference (AMI) attack carried out by a dishonest server in FL. In AMI attacks,the server crafts and embeds malicious parameters into global models toeffectively infer whether a target data sample is included in a client'sprivate training data or not. By exploiting the correlation among data featuresthrough a non-linear decision boundary, AMI attacks with a certified guaranteeof success can achieve severely high success rates under rigorous localdifferential privacy (LDP) protection; thereby exposing clients' training datato significant privacy risk. Theoretical and experimental results on severalbenchmark datasets show that adding sufficient privacy-preserving noise toprevent our attack would significantly damage FL's model utility.

Active Membership Inference Attack under Local Differential Privacy in Federated Learning