Grant Award Summary

The University of Oklahoma received a $291,099 CAREER Project Grant from the National Science Foundation's Division of Computer and Network Systems (CFDA 47.070: Computer and Information Science and Engineering) effective October 1, 2026, through September 30, 2031. This research initiative will develop domain knowledge-guided machine learning architectures to enhance wireless network security. The project delivers specialized learning models incorporating wireless-domain knowledge across three primary categories: centralized learning models, decentralized learning models, and large language models. Specific deliverables include a training-efficient, wireless-specific surrogate model for resource allocation attack analysis and a large language model-powered multi-agent framework addressing security tasks. The research advances wireless network security capabilities while creating training-efficient AI solutions tailored to mobile network protocol layer design considerations.

The project emphasizes broader impacts through educational advancement, including enhanced undergraduate student training opportunities and open dissemination of training materials via outreach activities. Three research thrusts grounded in system design and practical evaluation will address adversarial inference, adversarial generation, and data transformation tasks within modern complex and densely populated wireless networks. The initiative bridges the gap between wireless engineering domain expertise and machine learning efficiency by classifying and deterministically translating protocol-layer knowledge into AI-friendly representations suitable for deployment across different learning model architectures.