search

reds-lab / Narcissus

The official implementation of the CCS'23 paper, Narcissus clean-label backdoor attack -- only takes THREE images to poison a face recognition dataset in a clean-label way and achieves a 99.89% attack success rate.
https://arxiv.org/pdf/2204.05255.pdf
MIT License
105 stars 12 forks source link

Request for ViT poisons #10

Open opooladz opened 4 months ago

opooladz commented 4 months ago

Hi thanks for the great poisson.

I was wondering if you can provide some code to attack a ViT on CIFAR10 or imagenet.