Re:Images that fool computer vision raise security concerns
by JoeAltmaier on Monday March 23, 2015 @12:33PM
(#9251742)
Cool! And it would be so easy. Just show one of those noisy thumbnails, and see if the human can identify it as a 'panda'
Re:Images that fool computer vision raise security concerns
by saalweachter on Monday March 23, 2015 @08:25PM
(#9254192)
That's actually a fun-sounding research project: train humans to classify those images. I'd be very interested to know if humans could learn to classify either sets of images. They might not look like a 'panda' to us, but there is some underlying pattern that a machine can pick out and apply the arbitrary label 'panda' to. Can a human learn that same pattern?
Re:Images that fool computer vision raise security concerns
by JoeAltmaier on Tuesday March 24, 2015 @09:58AM
(#9256548)
Maybe so. But I was thinking, maybe there're weird patterns that human pattern-matching will erroneously classify as well. Probably unconsciously - if we look again, we'd say 'huh, that's just a mess of pixels'. So you'd have to flash them briefly and ask for an instant answer or something, to catch the pattern matcher before the cognitive check got done?
I get a mental image of a future where computers try to keep us pesky humans out of their websites.