Universal Adversarial Perturbations for Speech Recognition Systems
Conference of the International Speech Communication Association, 2019.
In this work, we demonstrate the existence of universal adversarial audio perturbations that cause mis-transcription of audio signals by automatic speech recognition (ASR) systems. We propose an algorithm to find a single quasi-imperceptible perturbation, which when added to any arbitrary speech signal, will most likely fool the victim ...More
PPT (Upload PPT)