Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
pavel_lishin
on March 23, 2015
|
parent
|
context
|
favorite
| on:
Images that fool computer vision raise security co...
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.
Consider applying for YC's W25 batch! Applications are open till Nov 12.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: