Re:Images that fool computer vision raise security concerns
by pavel_lishin on Monday March 23, 2015 @11:50AM
(#9251507)
That would be interesting; it could flag inputs that are ambiguous to humans but not machines (or vice versa, or when there's a discrepancy at all) since it could suggest that something shady is happening.
[ Parent
| on HN ]
There are no comments on this comment yet.