±¬ÁϹÏ

Rogue Unmanned Aerial Systems (UAS) pose significant threats to maritime operations due to their capabilities for surveillance and potential weaponization. Existing detection solutions are complex and fail to provide real-time, accurate detection, especially against evasive adversaries. Machine learning techniques offer a promising avenue, enabling the prediction and tracking of UAS actions by analyzing patterns in their behavior.

This project aims to develop privacy-preserving, non-invasive approaches to identify and counteract adversarial UAS, while maintaining ethical standards across jurisdictions.

To address the need for effective UAS detection, the project proposes using artificial intelligence to create a Radio Frequency (RF) Signal Classification Toolbox. This tool will monitor and classify wireless signals in maritime environments, identifying the presence and capabilities of adversarial UAS based on unique characteristics of their emitted signals. By accurately classifying these signals, maritime operators can gain insights into the capabilities of adversary transmitters, allowing them to remain informed without directly interacting with the UAS. This knowledge could also empower operators to disrupt adversarial communications when necessary, enhancing defense mechanisms without legal or ethical concerns.

Research at the Center for Secure and Intelligent Systems has already made strides in this area through work for the Naval Systems Warfare Center. Opportunities for funding from the Department of Defense and Small Business Innovation Research programs highlight the interest in this technology. Opportunities for knowledge sharing through various expositions and technology bridges promise further collaboration and development in the field, ensuring that advancements in UAS detection can be widely shared and utilized.

Sachin Shetty, Ph.D.
Executive Director, Center for Secure and Intelligent Critical System; Professor, Electrical and Computer Engineering;  ±¬ÁϹÏ