Towards Resistant Audio Adversarial Examples
Tom Dörr, Karla Markert, Nicolas M. Müller, Konstantin Böttinger · 2020
Adversarial examples tremendously threaten the availability and integrity of machine learning-based systems. While the feasibility of such attacks has been observed first in the domain of image processing, recent research shows that speech recognition is also susceptible to adversarial attacks. However, reliably bridging the air gap (i.e., making the adversarial examples work when recorded via a microphone) has so far eluded researchers.