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) is a distributed learning paradigm that enablesmultiple clients to collaborate on building a machine learning model withoutsharing their private data. Although FL is considered privacy-preserved bydesign, recent data reconstruction attacks demonstrate that an attacker canrecover clients' training data based on the parameters shared in FL. However,most existing methods fail to attack the most widely used horizontal FederatedAveraging (FedAvg) scenario, where clients share model parameters aftermultiple local training steps. To tackle this issue, we propose aninterpolation-based approximation method, which makes attacking FedAvgscenarios feasible by generating the intermediate model updates of the clients'local training processes. Then, we design a layer-wise weighted loss functionto improve the data quality of reconstruction. We assign different weights tomodel updates in different layers concerning the neural network structure, withthe weights tuned by Bayesian optimization. Finally, experimental resultsvalidate the superiority of our proposed approximate and weighted attack (AWA)method over the other state-of-the-art methods, as demonstrated by thesubstantial improvement in different evaluation metrics for image datareconstructions.

Approximate and Weighted Data Reconstruction Attack in Federated Learning