 |
ML Newsnew | past | best | rss | submit | about |
| Audio Adversarial Examples: Targeted Attacks on Speech-To-Text (arxiv.org) | |
| 3 points by YeGoblynQueenne on Jan 11, 2018 | hide | past | pdf | discuss on HN | |
|
In plain words: By nudging an audio waveform step by step while checking what the speech-to-text system would transcribe, they turn any recording into one that reads out a chosen phrase. The tweaked audio stayed over 99.9% similar to the original yet fooled the system every time. Abstract · Audio Adversarial Examples: Targeted Attacks on Speech-to-TextWe 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. | |
| add comment on HN |