Mathematical analysis

Artificial intelligence

Phrase

Mathematics

Domain (mathematical analysis)

Computer science

Speech coding

Construct (python library)

Computer network

Speech recognition

Adversarial system

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.

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