-
Hi, thanks for your benchmark work and the open source code. I have a question about the Hybrid-training part of the code.
In the code, adversarial point clouds produced by pgd,drop and add are mix…
-
Are you using the correct PGD Index equation in the code? The one that is in the paper is different. It seems that the following lines in the ```GradientMethod``` function
```
Mag_of_MeanGrad = sqrt…
-
on this line https://github.com/DSE-MSU/DeepRobust/blob/master/deeprobust/image/defense/pgdtraining.py#L219
`adversary = PGD(self.model)`
You guys forgot to pass in the self.device parameter, wh…
-
Hi， I trained mono FCOS3D and PGD model on my own dataset, but PGD performs more worse than FCOS3D both on bbox AP11 and the final detections. Could someone help me figure it out. The config models of…
-
Hello @EiffL, I've worked on the implementation of the PGD scheme in JAX.
In this [notebook ](https://github.com/DifferentiableUniverseInitiative/jaxpm-paper/blob/fcfe7f86d1a0cbb5ad2ae82b3803be38ac4…
-
Would there be an easy way to remove the need to have PGD-file before simulations? PGD-files contain information that is derived from the (spinup) namelists, and therefore changes in namelists do not …
-
Hello,
Q.1
is it possible to give list of epsilon for LinfPGD attacks? I wanted to test how a number of steps affect the result in terms of PGD attacks.
Q. 2
I would like to know how we could d…
-
We need to add a .kitchen.cloud.yml file to make sure the cookbook runs on openstack. The reason this wasn't done intially because I didn't want to fix too many moving parts at once.
-
Hi Jin
I meet some problems when I run the code pgd_test in graph global attack examples.
1. In line 37, why normalize the feature matrix? This do harms the performance of GCN on clean graphs.
…
-
Hi,
I am working on proof checking for Marabou proofs, and I wanted to raise a case where Marabou concludes that a query is UNSAT (during preprocessing), but running PGD adversarial attack seem to …