Google's AI Tool for Video Searches Can Be Easily Deceived
Monday, April 3, 2017 - 13:31
in Mathematics & Economics
University of Washington security researchers have shown that Google's new tool that uses machine learning to automatically analyze and label video content can be deceived by inserting a photograph periodically into videos. After they inserted an image of a car into a video about animals, for instance, the system thought the video was about an Audi.