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

Fast identification of new network attack patterns is crucial for improvingnetwork security. Nevertheless, identifying an ongoing attack in aheterogeneous network is a non-trivial task. Federated learning emerges as asolution to collaborative training for an Intrusion Detection System (IDS). Thefederated learning-based IDS trains a global model using local machine learningmodels provided by federated participants without sharing local data. However,optimization challenges are intrinsic to federated learning. This paperproposes the Federated Simulated Annealing (FedSA) metaheuristic to select thehyperparameters and a subset of participants for each aggregation round infederated learning. FedSA optimizes hyperparameters linked to the global modelconvergence. The proposal reduces aggregation rounds and speeds up convergence.Thus, FedSA accelerates learning extraction from local models, requiring fewerIDS updates. The proposal assessment shows that the FedSA global modelconverges in less than ten communication rounds. The proposal requires up to50% fewer aggregation rounds to achieve approximately 97% accuracy in attackdetection than the conventional aggregation approach.

FedSA: Accelerating Intrusion Detection in Collaborative Environments with Federated Simulated Annealing