Project STRIKE (Spectrum-Targeted Resilient ISR and non-Kinetic Effects)

By leveraging advanced 5G/FutureG technologies, high-performance computing, and state-of-the-art artificial intelligence/machine learning (AI/ML) techniques, such as deep neural networks, this research topic aims to optimize 5G/FutureG network configuration, resource allocation, and tactical edge processing in real time. Project STRIKE’s innovative approach to computing at the tactical edge ensures secure, adaptive, and resilient communications, even in degraded or contested environments. These capabilities provide critical advantages for the Air Force and the broader Department of Defense, ensuring operational superiority in increasingly complex and spectrum-congested battlespaces. 

FutureG and AI/ML technologies are indispensable for military advancement, providing not only secure and instantaneous access but also optimizing data processing, exploitation and dissemination (PED) capabilities.  With the ability to deliver higher data rates and lower latency while enhancing security measures, FutureG technologies coupled with AI/ML have the potential to unlock a myriad of capabilities related to several areas including: 

·       Big Data and Analytics within Open Radio Access Networks (ORAN)

·       Signal detection, classification and geolocation

·       Advanced security waveforms

·       Artificial Intelligence and Machine Learning in 5G/FutureG Network Analysis

·       Secure Low Probability of Intercept (LPI), Low Probability of Detect (LPD) and Anti-Jam Waveforms

·       Physical Layer Security utilizing Massive MIMO and millimeter-wave (mmWave) Technologies

·       Integrated Sensing, Communications and Cybersecurity

·       Agile spectrum sensing and dynamic spectrum utilization

·       Internet of Things (IoT) Networks and Aerial IOT Networks

·       Unmanned Aerial Systems (UAS) Swarms and Coalitions and Counter-UAS Swarms and Coalitions

Advancing the state-of-the-art in any or all of these areas has the potential to propel military capabilities to new heights, ensuring agility, efficiency, and resilience in an evolving security landscape.

[1] S. Rifat, J. Ashdown and F. Restuccia, “DARDA: Domain-Aware Real-Time Dynamic Neural Network Adaptation,” arXiv preprint arXiv:2409.09753, 2024.

[2] A. Owfi, J. Ashdown and K. Turck, “Online Meta-Learning Channel Autoencoder for Dynamic End-to-end Physical Layer Optimization,” arXiv preprint arXiv:2501.01608, 2025.

[3] H. Song, L. Liu, J. Ashdown and Y. Yi, “A Deep Reinforcement Learning Framework for Spectrum Management in Dynamic Spectrum Access,” IEEE Internet of Things Journal, vol. 8, no. 14, pp. 11208—11218, Jul. 2021.