“Based on deep learning development, ASR (automatic speech recognition) systems have become quite popular recently. Though deep learning in computer vision is known to be vulnerable to adversarial perturbations, little is known whether such perturbations are still valid on the practical speech recognition. We would like to embed the voice commands into a song, called CommandSong and escape human detection. Taking an open source toolkit, we succeed in crafting random songs into any commands “carrier” for the wav-to-API attack. In addition, our wav-air-API attack playing the CommanderSongs and decoding the recorded audio manages to achieve 94% success rate. In this way, the song carrying the command can spread through radio, TV or even any media player installed in the portable devices like smartphones, potentially impacting millions of users in long distance.”
– Commander Song - This technique embeds Amazon Echo, Google Home etc commands within songs in ways which make it impossible for humans to hear. (via newdarkage)