A team from Ruhr-Universität Bochum has succeeded in integrating secret commands for the Kaldi speech recognition system – which is believed to be contained in Amazon’s Alexa and many other systems – into audio files. These are not audible to the human ear, but Kaldi reacts to them. The researchers showed that they could hide any sentence they liked in different types of audio signals, such as speech, birds’ twittering, or music, and that Kaldi understood them. A virtual assistant that can carry out online orders is one of many examples where such an attack could be exploited.
— source news.rub.de | 24 Sep 2018