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
- 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)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2021.emnlp-main.241.pdf
- Data
- GLUE, IMDb Movie Reviews, SST, SST-2