Login / Signup
Red Alarm for Pre-trained Models: Universal Vulnerabilities by Neuron-Level Backdoor Attacks.
Zhengyan Zhang
Guangxuan Xiao
Yongwei Li
Tian Lv
Fanchao Qi
Zhiyuan Liu
Yasheng Wang
Xin Jiang
Maosong Sun
Published in:
CoRR (2021)
Keyphrases
</>
neural network
pre trained
statistical model
countermeasures
feature selection
prior knowledge
semi supervised