Image recognition technology may be sophisticated, but it is also easily duped. Researchers have fooled algorithms into confusing two skiers for a dog, a baseball for espresso, and a turtle for a rifle. But a new method of deceiving the machines is simple and far-reaching, involving just a humble sticker.
Google researchers developed a psychedelic sticker that, when placed in an unrelated image, tricks deep learning systems into classifying the image as a toaster. According to a recently submitted research paper about the attack, this adversarial patch is "scene-independent," meaning someone could deploy it "without prior knowledge of the lighting conditions, camera angle, type of classifier being attacked, or even the other items within the scene." It's also easily accessible, given it can be shared and printed from the internet.
(Score: 3, Interesting) by KritonK on Thursday January 11 2018, @09:25AM
I isolated the sticker from the paper, and did an image-based google search for it. The result was "artificial intelligence", with references to the work that produced the sticker.
I then pasted the sticker on an image of a banana, and did an image-based search for the combination. The result was "banana".
It seems that google have already updated their image recognition algorithms to account for the work in the paper. (Or, there never was a problem with the algorithms, and the paper is invalid.)