About Missing Clean Model for TrojanNN Attack Implementation about backdoorbench HOT 2 CLOSED

Sorry for confusion, clean_model.pth is actually the clean model trained without backdoor attack. For example, if you want to attack preactresnet18 on cifar10, then the clean_model.pt should be weight of preactresnet18 trained on cifar10.
Here is the link contains many clean_model.pth : https://drive.google.com/drive/folders/1lnCObVBIUTSlLWIBQtfs_zi7W8yuvR-2?usp=share_link

from backdoorbench.

Thank you very much for your response; this project has truly been a great help to me, and I appreciate your work and effort once again!
As mentioned before, I am trying to conduct a new defense research based on your project. In experiments using the ResNet-18 architecture and applied to two different datasets, I have tested seven different backdoor attack methods and achieved some results. However, I believe one of the key challenges in backdoor attack defense is determining whether a model has been implanted with a backdoor. If we cannot accurately determine this, we may need to test various defense methods on clean models to ensure they do not negatively affect clean models. But currently, based on your project, I feel that implementing this test seems somewhat difficult.
I would like to ask if you have any good suggestions or methods to help me complete this experiment? I would be extremely grateful for any guidance！

from backdoorbench.