Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-level Backdoor Attacks - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Zhengyan Zhang, Guangxuan Xiao, Yongwei Li, Tian Lv, Fanchao Qi, Zhiyuan Liu 0001, Yasheng Wang, Xin Jiang 0002, Maosong Sun. Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-level Backdoor Attacks. Int. J. Autom. Comput., 20(2):180-193, April 2023. [doi]

This author has not been identified. Look up 'Zhengyan Zhang' in GoogleThis author has not been identified. Look up 'Guangxuan Xiao' in GoogleThis author has not been identified. Look up 'Yongwei Li' in GoogleThis author has not been identified. Look up 'Tian Lv' in GoogleThis author has not been identified. Look up 'Fanchao Qi' in GoogleThis author has not been identified. Look up 'Zhiyuan Liu 0001' in GoogleThis author has not been identified. Look up 'Yasheng Wang' in GoogleThis author has not been identified. Look up 'Xin Jiang 0002' in GoogleThis author has not been identified. Look up 'Maosong Sun' in Google

runs on WebDSL