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 this paper, we initiate the study of local model reconstruction attacksfor federated learning, where a honest-but-curious adversary eavesdrops themessages exchanged between a targeted client and the server, and thenreconstructs the local/personalized model of the victim. The local modelreconstruction attack allows the adversary to trigger other classical attacksin a more effective way, since the local model only depends on the client'sdata and can leak more private information than the global model learned by theserver. Additionally, we propose a novel model-based attribute inference attackin federated learning leveraging the local model reconstruction attack. Weprovide an analytical lower-bound for this attribute inference attack.Empirical results using real world datasets confirm that our localreconstruction attack works well for both regression and classification tasks.Moreover, we benchmark our novel attribute inference attack against thestate-of-the-art attacks in federated learning. Our attack results in higherreconstruction accuracy especially when the clients' datasets areheterogeneous. Our work provides a new angle for designing powerful andexplainable attacks to effectively quantify the privacy risk in FL.

Local Model Reconstruction Attacks in Federated Learning and their Uses