News for hackers. Stuff that matters.

A comment on One pixel attack for deceiving deep neural networks. Parent comment

Re:One pixel attack for deceiving deep neural networks by kumarvvr on Sunday October 29, 2017 @01:36AM (#15578098)
Is getting to know the model of the classifier so difficult? I mean, for an API, is it not possible to deduce the internal structure of the system based on the Input-output combination?? Just asking.
[ Parent | on HN ]
Re:One pixel attack for deceiving deep neural networks by mattnewton on Sunday October 29, 2017 @02:34AM (#15578217)
If by internal structure gp means the number or structure of the layers, then no, it’s not feasible to deduce this.

If they write regular blog posts or publish the architecture in a journal however, and the api gives you probabilities, you could maybe recreate it with a process similar to distillation?

[ Parent | on HN ]