Work

Universal Adversarial Perturbations for Speech Recognition Systems

Year: 2019
Type: conference-paper
Abstract: 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 speech recognition model. Our experiments demonstrate the application of our proposed technique by crafting audio-agnostic universal perturbations for the state-of-the-art ASR system -- Mozilla DeepSpeech. Additionally, we show that such perturbations generalize to a significant extent across models that are not available during training, by performing a transferability test on a WaveNet based ASR system.
Language: English
Open Access status: green
OpenAlex ID: W2943984343
FWCI: 5.545
Cites: 33
Cited by: 174
Related to: 10