-
**Describe the bug**
For the same model, I can compute output bounds successfully for some choices of epsilon-balls, but receive 2 different errors for some other choices of the epsilon-ball. These e…
-
Hello and thank you for this amazing tool!
I have also tried to use alpha-beta-CROWN with the same setup but had the same error in the title.
You can find the issue here: https://github.com/Veri…
-
Hi! Thank you for the reply to the question about the 'CROWN' repository!
I want to calculate the minimum r as the same as the 'CROWN', and I tried the code as follows:
def test(input,model):
eps =…
-
I want to use ab-crown to verify neural networks with localrobustness property with the l-1 and l-2 norms. When I do this I get "Only Linf-norm attack is supported, the pgd_order will be changed to sk…
-
I am trying to compute bounds on multiple models in parallel using the `multiprocessing` library. This works fine when using IBP or CROWN, but when using `alpha-CROWN`, I get very nondescript (fatal) …
-
I am trying to apply your losses and optimizer to other models and applications. What are the steps to do? Is it just wrapping my model with this `VerifiableModelWrapper` or should I do more?
-
Hi,
When I run the CROWN verified error with let's say \epsilon = 0.3, what's the exact meaning of the terms in the output like Loss, CE loss etc.? I'd like to estimate or desume a lower bound with…
-
**Describe the bug**
I was delighted to see that `auto_LiRPA` can bound ConvTranspose layers out of the box, but, unfortunately, CROWN in batch mode doesn't seem to work.
**To Reproduce**
Code to…
-
Hi,
I've encountered a few issues while using alpha-beta-CROWN for verifying the output of a simple neural network. I would greatly appreciate your assistance in resolving these concerns.
I hav…
-
Thanks for your great work, but I have some question when using auto_LiRPA
I would like to know if the auto_LiRPA tool can handle networks that include multiplication operations. If so, how should …