reds-lab / asset Goto Github PK

Thanks for sharing your amazing work!

I noticed that the loss function of the inner loop shoulde be binary cross entropy loss but in demo it was assigned as MSEloss, I wonder is it has a side effect on the final result.

Additionally, I've noted that the 'o_model', which was referenced in #1 and utilized in the inner loop, is trained with a poison rate of 0.1, while the 'train_dataset' in the demo has a poison rate of 0.05. My understanding is that the 'o_model' should be trained on the same poisoned 'train_dataset'. However, it appears that they are not identical. I'm wondering if this discrepancy could also influence the final results.

Thanks for sharing your amazing work!

Could you release code for SSL?

What is your details about backdoor attack SSL on C-brd, C-squ on Cifar10? how does 0.5% comes? There are 5000 samples in each class for Cifar10, how do you distribute the 250 poison sample among classes?