AI can now defend itself against malicious messages hidden in speech.
Sign Up to like & getrecommendations! Published in 2019 at "Nature"
DOI: 10.1038/d41586-019-01510-1
Abstract: Computer scientists have thwarted programs that can trick AI systems into classifying malicious audio as safe. Computer scientists have thwarted programs that can trick AI systems into classifying malicious audio as safe. read more here.
Keywords: defend malicious; hidden speech; messages hidden; malicious messages ... See more keywords