LC attack source
Closed this issue · 1 comments
yyang318 commented
Very nice work. May I confirm that the LC attack is Label-Consistent Backdoor Attacks as shown in this project. In the paper, the LC attack cites the paper Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks.
CHR-ray commented
Yes, that's a typo. Sorry to confuse you. LC is for Label-Consistent Backdoor Attacks, not poison frogs.
You can refer to resource/label-consistent and utils/bd_img_transform/lc.py for more information.