Protecting Wireless Systems from Adversarial Attacks

ECE William Lincoln Smith Professor Tommaso Melodia, Assistant Professor Francesco Restuccia, and Assistant Research Professor Salvatore D’oro were awarded a patent for “Neural Network for Adversarial Deep Learning in Wireless Systems.”

Abstract Source: USPTO

A method of determining a response of a radio frequency wireless communication system to an adversarial attack is provided. Adversarial signals from an adversarial node are transmitted to confuse a target neural network of the communication system. An accuracy of classification of the incoming signals by the target neural network is determined.

Related Faculty: Tommaso Melodia, Francesco Restuccia, Salvatore D'Oro

Related Departments:Electrical & Computer Engineering