Question for the implementation of Neural cleanse(NC)

[mo666666]

On page 16 of the BackdoorBench NeurIPS2022 paper, I noticed that NC is introduced as a method that first detects the backdoored model and then mitigates it through pruning based on the searched trigger. However, for the code in this repo, I find that you perform unlearning instead of pruning. Is that a common operation for the implementation of NC?

[mdzhangst]

Yes unlearn is a common approach to backdoor triggers, and later articles have taken advantage of the idea of unlearn to solve problems

[mo666666]

Ok, thank you for your reply!