Global ETD Search

Adversarial RFML: Evading Deep Learning Enabled Signal Classification

Flowers, Bryse AustinVirginia Tech2019

… radio resources, as well as detect and classify signals. While there are numerous advantages to RFML, this thesis answers the question "is it secure?" DNNs have been shown, in other applications such as Computer Vision (CV), to be vulnerable to what are known as adversarial evasion attacks, which …

vt Repository record for Adversarial RFML: Evading Deep Learning Enabled Signal Classification (opens in a new tab)