Is this project an undergraduate, graduate, or faculty project?
Graduate
Project Type
individual
Campus
Daytona Beach
Authors' Class Standing
Jessica Christa Wira, Graduate Student
Lead Presenter's Name
Jessica Christa Wira
Lead Presenter's College
DB College of Arts and Sciences
Faculty Mentor Name
Dumindu Samaraweera
Abstract
The rise of Connected and Autonomous Vehicles (CAVs) has led to a rapid increase in privacy-sensitive driving data, requiring secure and efficient learning frameworks. Federated Learning (FL) enables collaborative model training without sharing raw data. However, FL remains vulnerable to inference attacks, model poisoning, and data breaches, requiring additional privacy safeguards. Among various privacy-enhancing mechanisms, Homomorphic Encryption (HE) stands out as a promising solution, enabling computations on encrypted data while ensuring confidentiality throughout the FL process. This research provides a comprehensive review of HE-based FL for CAVs, covering HE schemes, optimization techniques, practical limitations, and hybrid privacy-enhancing approaches. Additionally, we identify open research challenges and future directions to improve the scalability, efficiency, and security of HE-FL. This study aims to support researchers in designing robust, privacy-preserving FL frameworks for next-generation CAV networks.
Did this research project receive funding support (Spark, SURF, Research Abroad, Student Internal Grants, Collaborative, Climbing, or Ignite Grants) from the Office of Undergraduate Research?
No
Homomorphic Encryption-Based Federated Learning for CAVs
The rise of Connected and Autonomous Vehicles (CAVs) has led to a rapid increase in privacy-sensitive driving data, requiring secure and efficient learning frameworks. Federated Learning (FL) enables collaborative model training without sharing raw data. However, FL remains vulnerable to inference attacks, model poisoning, and data breaches, requiring additional privacy safeguards. Among various privacy-enhancing mechanisms, Homomorphic Encryption (HE) stands out as a promising solution, enabling computations on encrypted data while ensuring confidentiality throughout the FL process. This research provides a comprehensive review of HE-based FL for CAVs, covering HE schemes, optimization techniques, practical limitations, and hybrid privacy-enhancing approaches. Additionally, we identify open research challenges and future directions to improve the scalability, efficiency, and security of HE-FL. This study aims to support researchers in designing robust, privacy-preserving FL frameworks for next-generation CAV networks.