Radiofrequency Ensemble Classifier

To address the Navy’s need for trustworthy artificial intelligence (AI) systems that are resilient to adversarial attacks, Intellisense Systems, Inc. proposes in Phase II, to advance the development of the new Radiofrequency Ensemble Classifier (RADEC) system based on an ensemble of complimentary classifiers trained on randomly transformed/augmented radiofrequency (RF) data. Specifically, the innovation in using a novel meta-learning genetic algorithm to optimally select the most effective set of complimentary classifiers will enable RADEC to successfully identify adversarial examples and thus determine whether standard (i.e., unhardened) AI systems can be used to interpret incoming RF data correctly without falling prey to enemy deception. As a result, RADEC will provide the Navy the capability to develop resilient AI systems by (1) understanding failure modes of standard AI systems and (2) mitigating potential deceit of those AI systems. In Phase I, Intellisense developed and demonstrated feasibility of RADEC’s ability to detect and correctly classify adversarial examples for RF automatic modulation classification in simulated and real (over-the-air) data. During Phase II, Intellisense will complete the algorithmic development of RADEC based on lessons learned from Phase I, test RADEC in high-fidelity operationally representative scenarios dealing with electronic warfare, and deliver a prototype for testing and evaluation. In addition, during Phase II Intellisense will coordinate with the Navy sponsor including PMA-265 (for the EA 18G) and the Naval Air Warfare Center Aircraft Division (NAWCAD), and Lockheed Martin Missiles and Fire Control to prepare to transition RADEC to Navy use in Phase III.