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.
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}
}