talrub

Hi, If i want to compare the robustness of the Vanilla RNN to that of the Vanilla RNN without the activation function in the recurrent, should i use the closed-form...

set_normalization_used

4

### ❔ Any questions Hi, According to attack.py line 501, it seems that if I perform atk.set_normalization_used(mean=[...], std=[...]) before applying the attack, the inputs will be denormalized (by self.inverse_normalize(inputs)). Can...

[BUG] Applying attacks on 2 instances of the same model gives too far away results

1

### ✨ Short description of the bug [tl;dr] I have conducted experiments with two instances of the same "4-layer-VanillaRNN-none_activation_between_layers" model , which I'll denote as model1 and model2. Both models...

Hi, Could you please upload your code for section 7 (ROBUSTNESS WITH RESPECT TO PERTURBATIONS) , which creates Table 3 ?