This $249,991 Project Grant award from the National Science Foundation's Computer and Information Science and Engineering (CFDA 47.070) program supports the development of an edge-friendly cyberinfrastructure that enables federated learning (FL) to be deployed for intelligent transportation system (ITS) applications in an efficient, secure, and privacy-preserving manner. The research aims to bring advances to transportation applications like naturalistic driving studies and traffic conflict prediction, and the proposed software tools will be open-sourced to benefit the broader ITS community. Key focus areas include investigating the interplay between FL and ITS efficiency, providing security tools against model/data attacks, and developing privacy-preserving FL architectures. The award recipient, Trustees of Indiana University, will establish a real distributed testbed with NVIDIA Jetson Nano devices to test the proposed methods. This project runs from January 1, 2024 to August 31, 2026.
Generated 8/13/24, 6:06 AM