Biblio
Filters: Keyword is audio waveform [Clear All Filters]
.
2018. Audio Adversarial Examples: Targeted Attacks on Speech-to-Text. 2018 IEEE Security and Privacy Workshops (SPW). :1–7.
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.