God bless you and keep you from harm, this day and forever.
Repost
HOW TO BREAK IMAGE CLASSIFIERS
simple, effective, simple, effective, enchanted anthropoids unchained, simple, effective, actually matters, disenchantment, effective, simple sabotage convolutional neural NPC networks, cnn, simple effective …beep, beep, beep
We present a method to create universal, robust, targeted adversarial image patches in the real world. The patches are universal because they can be used to attack any scene, robust because they work under a wide variety of transformations, and targeted because they can cause a classifier to output any target class. These adversarial patches can be printed, added to any scene, photographed, and presented to image classifiers; even when the patches are small, they cause the classifiers to ignore the other items in the scene and report a chosen target class.
Adversarial examples have been shown to
generalize to the real world
last in red because it important.
fuuug here's the paper.