ECE Associate Professor Salim El Rouayheb is the recipient of a new ARL award for the project titled "DAST: Dynamic, Adaptive, and Swift AI at the Resource-Constrained Tactical Networks." Dr. El Rouayheb is a co-PI on this three-year $1,400,000.00 collaborative effort between Rutgers and the University of Illinois at Chicago (UIC). Rutgers’ share of the award is $ $466,666.
The project will develop DAST, a Dynamic, Adaptive, and Swift AI framework for resource-constrained tactical networks. DAST will improve AI solution speed, accuracy, and security against adversarial attacks. DAST's development will involve creating multi-modal model-distributed inferencing, optimizing traffic management with a focus on large language models (LLMs), integrating decentralized learning and data mobility, and ensuring robustness against adversarial attacks. Moreover, we will develop a heterogeneous distributed computing testbed consisting of commodity end devices and edge servers and implement DAST algorithms in this testbed.