Universal adversarial perturbations for speech recognition systems

Paarth Neekhara, Shehzeen Hussain, Prakhar Pandey, Shlomo Dubnov, Julian McAuley, Farinaz Koushanfar

Research output: Contribution to journalConference articlepeer-review

31 Scopus citations

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.

Original languageEnglish
Pages (from-to)481-485
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume2019-September
DOIs
StatePublished - 1 Jan 2019
Externally publishedYes
Event20th Annual Conference of the International Speech Communication Association: Crossroads of Speech and Language, INTERSPEECH 2019 - Graz, Austria
Duration: 15 Sep 201919 Sep 2019

Keywords

  • Adversarial examples
  • Computer security
  • Speech processing
  • Speech recognition

Fingerprint

Dive into the research topics of 'Universal adversarial perturbations for speech recognition systems'. Together they form a unique fingerprint.

Cite this