Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning.

Linyang Li Demin Song Xiaonan Li Jiehang Zeng Ruotian Ma Xipeng Qiu

Published in: EMNLP (1) (2021)

Keyphrases

pre trained
probabilistic model
real time
neural network
wide range
face recognition
training data
viewpoint