Unmanned Aerial Vehicles (UAVs) have found wide use in various tasks, but developing swarm intelligence for intrusion detection is far from easy. In this project, we propose to leverage recent advances in large multimodal models (LMMs) that can fuse multiple data sources for secure missions. Our project will fine-tune and deploy LMMs of varying sizes to the edge/fog UAVs, combining data sources such as sensory inputs (e.g., camera, IMU) as well as internal operational data (e.g., syscall logs). This will enable real-time detection and response system to thwart threats with swarm-wide coordination, addressing Challenge #2 outlined by the GENZERO workshop. Moreover, we aim to perform hardware-in-the-loop tests, with real devices, data, and scenarios, leveraging University of Michigan’s M-Air 10,000 sq ft, four-story, testing facility. We envision that the final outcome will be an integrated system and demo validated in M-Air, achieving Technology Readiness Level 4 (TRL4).