Why won't anyone believe there really are subliminal messages corrupting young digital assistants?

Subject: General Tech | January 31, 2018 - 01:04 PM |
Tagged: siri, security, google, Alexa

Some of us are old enough to remember when certain parties were convinced there were subliminal messages in the music which kids listened to which they creatively blamed for a wide variety of behaviour.  This belief turned out to be as ridiculous as it sounds, though that doesn't stop it from recurring every couple of generations.  There is a somewhat similar and very real issue which The Register talks about here; using a deep neural net they were able to modify songs in such a way that digital assistants such as Echo, Siri and others would hear and execute a command while the humans in the room would only hear a slight distortion in the audio.  This particular method is much harder to protect against than the previously discovered vulnerability which was ultrasonic commands which a microphone could pick up but was well beyond the range of human hearing. 

You do need to reverse engineer the audio processing software of the digital assistant before you will be able to craft your hidden commands, however once that is done this is a very effective attack.

View Full Size

"The researchers tested a variety of in-song commands delivered directly to Kaldi as audio recordings, such as: "Okay Google, read mail" and "Echo, open the front door." The success rate of these was 100 per cent."

Here is some more Tech News from around the web:

Tech Talk

Source: The Register

Video News


January 31, 2018 | 01:51 PM - Posted by Kommando Kodiak (not verified)

Imagine hackers hacking the sound system of a stadium and uploading the songs or an electronics stores bank of tvs share a single source.

January 31, 2018 | 05:29 PM - Posted by Anonymously Anonymous (not verified)

oh, the hilarious pranks one could do to others while on game console and the other players are not wearing headphones.

Post new comment

The content of this field is kept private and will not be shown publicly.
  • Lines and paragraphs break automatically.
  • Allowed HTML tags: <a> <em> <strong> <cite> <code> <ul> <ol> <li> <dl> <dt> <dd> <blockquote><p><br>
  • Web page addresses and e-mail addresses turn into links automatically.

More information about formatting options

CAPTCHA
This question is for testing whether you are a human visitor and to prevent automated spam submissions.