Open AccessSecurity of Federated Learning: Attacks, Defensive Mechanisms, and Challenges
Author(s) -
Mourad Benmalek,
Mohamed Ali Benrekia,
Yacine Challal
Publication year - 2022
Publication title -
revue d'intelligence artificielle
Language(s) - English
Resource type - Journals
eISSN - 1958-5748
pISSN - 0992-499X
DOI - 10.18280/ria.360106
Subject(s) - computer science , federated learning , computer security , tracing , train , private information retrieval , data science , internet privacy , artificial intelligence , cartography , geography , operating system
Recently, a new Artificial Intelligence (AI) paradigm, known as Federated Learning (FL), has been introduced. It is a decentralized approach to apply Machine Learning (ML) on-device without risking the disclosure and tracing of sensitive and private information. Instead of training the global model on a centralized server (by aggregating the clients’ private data), FL trains a global shared model by only aggregating clients’ locally-computed updates (the clients’ private data remains distributed across the clients’ devices). However, as secure as the FL seems, it by itself does not give the levels of privacy and security required by today’s distributed systems. This paper seeks to provide a holistic view of FL’s security concerns. We outline the most important attacks and vulnerabilities that are highly relevant to FL systems. Then, we present the recent proposed defensive mechanisms. Finally, we highlight the outstanding challenges, and we discuss the possible future research directions.