Certifying robustness on custom network about recurjac-and-crown HOT 2 OPEN

@lhfowl Thank you for your interests in our work!

Currently this repository only provides a proof-of-concept implementation, and its implementation does not include convolutional layers (this is absolutely within by our theoretical framework but just unimplemented). Following the instructions you will be able to certify any MLP networks.

We are currently working on a re-implementation of RecurJac and CROWN that works with Pytorch and supports most common layers. I will let you know once that is ready.

from recurjac-and-crown.

Hi @lhfowl,

A new implementation of CROWN/Fast-Lin is available here:
https://github.com/huanzhang12/CROWN-IBP

It uses PyTorch and supports CNN layers. You can try it out - it should at least be useful for verifying a VGG like architecture.

from recurjac-and-crown.