Re:Images that fool computer vision raise security concerns
by jgrowl on Monday March 23, 2015 @12:27PM
(#9251717)
It makes me chuckle thinking about machine intelligence being able to solve a captcha when humans can't.
I get a mental image of a future where computers try to keep us pesky humans out of their websites.
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?
Also, one could make CAPTCHA's incredibly hard. Humans and dumb computers won't be able to solve it, and singular AI's get a pass. So give access to anyone who isn't able to solve the CAPTCHA and redirect the singularity AIs to google.com :).
Finally, the singular AI could create a CAPTCHA which separates humans from AI. The problem of separating humans from AI will quickly become too difficult for humans to solve.