loading page

Privacy and Security Challenges in Federated Learning for UAV Systems: A Comprehensive Review
  • +1
  • Ahmed Al Farsi,
  • Ajmal Khan,
  • Muhammad Rizwan,
  • Mohammed M. Bait-Suwailam
Ahmed Al Farsi
Sultan Qaboos University Water Research Center
Author Profile
Ajmal Khan
Sultan Qaboos University Water Research Center
Author Profile
Muhammad Rizwan
Sultan Qaboos University
Author Profile
Mohammed M. Bait-Suwailam
Sultan Qaboos University Water Research Center

Corresponding Author:msuwailem@squ.edu.om

Author Profile

Abstract

Unmanned Aerial Vehicles (UAVs) have become indispensable assets in various sectors, leveraging their mobility and data collection capabilities. However, privacy and security concerns have fueled interest in Federated Learning (FL) as a solution. FL, decentralized and collaborative, offers promise in addressing privacy risks inherent in centralized data processing while enhancing model performance. In this review, we explore FL’s privacy and security implications in UAV ecosystems. We highlight FL’s potential to mitigate privacy risks by aggregating model updates locally, minimizing data transmission needs. Additionally, we examine security challenges and evaluate protective mechanisms. Through a systematic literature review, we identify gaps and propose future research directions, aiming to enhance the security and privacy of FL in UAV applications.
15 Jul 2024Submitted to Security and Privacy
15 Jul 2024Submission Checks Completed
15 Jul 2024Assigned to Editor
15 Jul 2024Review(s) Completed, Editorial Evaluation Pending
21 Jul 2024Reviewer(s) Assigned