How to solve shadownet's channel random permutation？

[houndpan]

I was impressed by the approach outlined in Appendix D for removing the kernel mask. However, I'm still unclear about how to handle channel order permutations. Could you please provide some guidance on how to address this?

[ziqi-zhang]

The insight is that the weight distribution should be similar between models, so we use the weight information of a public model to recover the permutate. For example, we can use the pretrained model on the Internet and compare that model with the target model to recover the permutate.

[MaverickPigoo]

Is there available code that corresponds to the recovery of the filter permutation during your attack on ShadowNet?

[houndpan]

What methods can be employed to assess the similarity between two kernels? Can statistical metrics be utilized for this purpose? However, the permutation of channel orders poses a challenge, rendering many statistical metrics ineffective, such as cosine similarity.

If possible, could you provide some reference papers that address this issue?