Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
dTal
on Oct 29, 2016
|
parent
|
context
|
favorite
| on:
Universal adversarial perturbations
What happens if you include the perturbations in your training data?
dandermotj
on Oct 29, 2016
[–]
If my understanding is correct, the perturbations are inherent in the model, not the data. It's a vulnerability in the high dimensional decision boundary of n nets.
Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
