most citedRed Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks

40 citations · 40 across the 1 of their papers we have counts for

collaborators

1 paper

cs.CL2021★ 40 cited

Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks

Zhengyan Zhang, Guangxuan Xiao, Yongwei Li +6

Pre-trained models (PTMs) have been widely used in various downstream tasks. The parameters of PTMs are distributed on the Internet and may suffer backdoor attacks. In this work, w…