Wednesday, 1 March 2017

Google's anti-trolling AI can be defeated by typos, researchers find [Updated] - Ars Technica


Ars Technica

Google's anti-trolling AI can be defeated by typos, researchers find [Updated]
Ars Technica
By gaming the AI's parsing of text, they were able to get scores that would allow comments to pass a toxicity test that would normally be flagged as abusive. "One type of the vulnerabilities of machine learning algorithms is that an adversary can ...
Google's troll-fighting AI can be defeated by typosBoing Boing

all 4 news articles »


from The Idiot Test - Google News http://ift.tt/2lATnUg

No comments:

Post a Comment