Federated learning security mechanisms for protecting sensitive data

Asraa A. Abd Al-Ameer, Wesam Sameer Bhaya


One of the new trends in the field of artificial intelligence is federated learning (FL), which will have promising roles in many real-world applications due to the work characteristics of its architecture. The learning mechanism for this technique is based on making training in a distributed manner on the local data for each client using decentralized data, then collecting parameters for each local training and uploading it to the server, which in turn will send model updates to all clients to give the final learning result. To provide a broad study on FL from security and privacy aspects, this research paper introduces a general view of FL and its categories, most attacks that can befall it, the safety mechanisms used by existing works in attacks defense, enhancing the safety and privacy of FL whether in the transmission or collecting of data. Then, the usage of FL in network security by many research papers has been presented, and how good results were achieved, and finally a comparison has been made between these papers.


Artificial intelligence; Distributed machine learning; Federated learning; Machine learning; Network security; Privacy; Security

Full Text:


DOI: https://doi.org/10.11591/eei.v12i4.4751


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Bulletin of EEI Stats

Bulletin of Electrical Engineering and Informatics (BEEI)
ISSN: 2089-3191, e-ISSN: 2302-9285
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).