English

Audio Adversarial Examples: Targeted Attacks on Speech-to-Text

Machine Learning 2018-04-02 v2 Artificial Intelligence Cryptography and Security

Abstract

We construct targeted audio adversarial examples on automatic speech recognition. Given any audio waveform, we can produce another that is over 99.9% similar, but transcribes as any phrase we choose (recognizing up to 50 characters per second of audio). We apply our white-box iterative optimization-based attack to Mozilla's implementation DeepSpeech end-to-end, and show it has a 100% success rate. The feasibility of this attack introduce a new domain to study adversarial examples.

Keywords

Cite

@article{arxiv.1801.01944,
  title  = {Audio Adversarial Examples: Targeted Attacks on Speech-to-Text},
  author = {Nicholas Carlini and David Wagner},
  journal= {arXiv preprint arXiv:1801.01944},
  year   = {2018}
}
R2 v1 2026-06-22T23:37:53.617Z