- Adversarial learning technique identifies rogue RF transmitters and classifies trusted ones using generative adversarial nets (GAN)
- Implementation framework offers an end-to-end solution for transmitter fingerprinting and identification using raw IQ data
The invention relates to an adversarial learning technique for identifying rogue RF transmitters and classifying trusted ones by designing and implementing generative adversarial nets (GAN). Understanding and analyzing the radio frequency (RF) environment have become indispensable for various autonomous wireless deployments. Machine learning techniques have become popular as they can learn, analyze and even predict the RF signals and associated parameters that characterize an RF environment. However, classical machine learning methods have their limitations and there are situations where such methods become ineffective—such as when active adversaries are present and try to disrupt the RF environment through malicious activities like jamming or spoofing. The technology was developed jointly by the University of Central Florida, the University of Alabama, and the U.S. Air Force Research Laboratory.