Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
arXiv: Audio and Speech Processing, 2019.
Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in the image domain. In this domain, adversarial examples can be constructed by imperceptibly modifying images to cause misclassification, and are practical in th...More
PPT (Upload PPT)