Boffins bust AI with corrupted training data

https://regmedia.co.uk/2015/02/10/smart_tv_spying.jpg?x=442&y=293&crop=1

If you don’t know what your AI model is doing, how do you know it’s not evil?

Boffins from New York University have posed that question in a paper at arXiv, and come up with the disturbing conclusion that machine learning can be taught to include backdoors, by attacks on their learning data.

Tags: 

Read more: Boffins bust AI with corrupted training data

Story added 28. August 2017, content source with full text you can find at link above.