Header /5611/boinboing report this ad / Cory Doctorow / 9:28 am Wed Mar 29, 2017 /5611/boinboing See all deals /5611/boinboing Twitter Facebook RSS In a newly revised paper in Computer Vision and Pattern Recognition , a group of French and Swiss computer science researchers show that "a very small perturbation vector that causes natural images to be misclassified with high probability" -- that is, a minor image transformation can beat machine learning systems nearly every time. /5611/boinboing report this ad What's more, the researchers show evidence that similar tiny distortions exist in other kinds of data-types that confound all machine-learning systems! The "universal adversarial preturbation" changes images in ways that are imperceptible to the human eye, but devastating to machine vision. The research is typical of ...