Backdoor attacks on pre-trained models by layerwise weight poisoning

L Li, D Song, X Li, J Zeng, R Ma, X Qiu - arXiv preprint arXiv:2108.13888, 2021 - arxiv.org
\textbf {P} re-\textbf {T} rained\textbf {M} odel\textbf {s} have been widely applied and recently
proved vulnerable under backdoor attacks: the released pre-trained weights can be …

Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning

L Li, D Song, X Li, J Zeng, R Ma… - Proceedings of the 2021 …, 2021 - aclanthology.org
Abstract Pre-Trained Models have been widely applied and recently proved vulnerable
under backdoor attacks: the released pre-trained weights can be maliciously poisoned with …

Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning

L Li, D Song, X Li, J Zeng, R Ma, X Qiu - arXiv e-prints, 2021 - ui.adsabs.harvard.edu
Abstract\textbf {P} re-\textbf {T} rained\textbf {M} odel\textbf {s} have been widely applied and
recently proved vulnerable under backdoor attacks: the released pre-trained weights can be …

[PDF][PDF] Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning

L Li, D Song, X Li, J Zeng, R Ma, X Qiu - scholar.archive.org
Abstract Pre-Trained Models have been widely applied and recently proved vulnerable
under backdoor attacks: the released pre-trained weights can be maliciously poisoned with …