Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning

Linyang Li, Demin Song, Xiaonan Li, Jiehang Zeng, Ruotian Ma, Xipeng Qiu


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 certain triggers. When the triggers are activated, even the fine-tuned model will predict pre-defined labels, causing a security threat. These backdoors generated by the poisoning methods can be erased by changing hyper-parameters during fine-tuning or detected by finding the triggers. In this paper, we propose a stronger weight-poisoning attack method that introduces a layerwise weight poisoning strategy to plant deeper backdoors; we also introduce a combinatorial trigger that cannot be easily detected. The experiments on text classification tasks show that previous defense methods cannot resist our weight-poisoning method, which indicates that our method can be widely applied and may provide hints for future model robustness studies.
Anthology ID:
2021.emnlp-main.241
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3023–3032
Language:
URL:
https://aclanthology.org/2021.emnlp-main.241
DOI:
10.18653/v1/2021.emnlp-main.241
Bibkey:
Cite (ACL):
Linyang Li, Demin Song, Xiaonan Li, Jiehang Zeng, Ruotian Ma, and Xipeng Qiu. 2021. Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3023–3032, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning (Li et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.241.pdf
Data
GLUEIMDb Movie ReviewsSSTSST-2