AIbase
Product LibraryTool Navigation

Narcissus

Public

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.

Creat2022-04-09T04:49:53
Update2025-03-13T15:51:35
https://arxiv.org/pdf/2204.05255.pdf
110
Stars
0
Stars Increase