Giters

carlini / nn_robust_attacks

Robust evasion attacks against neural network to find adversarial examples

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

no boxmin and boxmax in L_0 and L_inf

CNOCycle opened this issue · comments

commented

Hi author,

I'm developing a robust model.

For some mathematical reasons, input images should be defined in range [0, 1].

However, attacks are implemented by tanh which range is [-0.5, 0.5].

L_0 and L_inf do not provide any parameters boxmin and boxmax to shift range to [boxmin, boxmax].

Someone implement configurable range in L_2 attack.

  • commit b5925dd
    | Author: w
    | Date: Wed Oct 18 09:05:25 2017 +0800
    |
    | Make range of box constraints configurable
    |

Can we safely modify L_0 and L_inf attacks based on this commit?