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

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

The pre-training-then-fine-tuning paradigm has been widely used in deep learning. Due to the huge computation cost for pre-training, practitioners usually download pre-trained models from the Internet and fine-tune them on downstream datasets, while the downloaded models may suffer backdoor attacks....

Full description

Bibliographic Details
Main Authors: Zhang, Zhengyan, Xiao, Guangxuan, Li, Yongwei, Lv, Tian, Qi, Fanchao, Liu, Zhiyuan, Wang, Yasheng, Jiang, Xin, Sun, Maosong
Format: Article
Language:English
Published: Springer Science and Business Media LLC 2024
Online Access:https://hdl.handle.net/1721.1/155692

Internet

https://hdl.handle.net/1721.1/155692

Similar Items