Tech News

Simple typos tripped up Google's hate speech detection

September 11, 2018

Keeping on top of negativity online is a difficult task, with nearly one in five Americans having experienced severe online harassment. Google’s Perspective AI aims to fix those problems, but it doesn’t seem to be as smart as it needs to be.

As TNW reports, a group of researchers at Aalto University and the University of Padua have discovered Google’s artificial intelligence can easily be tricked and that state-of-the-art hate speech detection models only perform well when tested by the same type of data they were trained on. Simple tricks to get around Google’s AI include: inserting typos; adding spaces between words; or adding unrelated words to the original sentence. Read more…

More about Hate Speech, Google Ai, Tech, and Artificial Intelligence
Source: Mashable | Simple typos tripped up Google's hate speech detection

No Comments

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.