October 31, 2017 07:37 am PDT
Original Link: http://feeds.boingboing.net/~r/boingboing/iBag/~3/dYBMvBKD8jU/classifiers-are-fragile.html
Researchers can fool machine-learning vision systems with a single, well-placed pixel
Three researchers from Kyushu University have published a paper describing a means of reliably fooling AI-based image classifiers with a single well-placed pixel. (more…)
Original Link: http://feeds.boingboing.net/~r/boingboing/iBag/~3/dYBMvBKD8jU/classifiers-are-fragile.html
Share this article:
Tweet
View Full Article