axbom’s Twitter Archive
—№ 23,728
⇤ Newest
Tweet
⇠ Newer
Tweet
Older
Tweet
⇢
With this method, no matter what an audio file sounds like, the text output will be whatever the attacker wants it to be.
thenextweb.com/artificial-intelligence/2018/01/11/ai-learns-how-to-fool-text-to-speech-thats-bad-news-for-voice-assistants/
On twitter.com
❤️ 1
Favorite
2018 Jan 11
Mood +
2
🙂