Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models

Shuai Zhao, Jinming Wen, Anh Tuan Luu, Junbo Zhao, Jie Fu. Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models. In Houda Bouamor, Juan Pino 0001, Kalika Bali, editors, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023. pages 12303-12317, Association for Computational Linguistics, 2023. [doi]

@inproceedings{ZhaoWLZF23,
  title = {Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models},
  author = {Shuai Zhao and Jinming Wen and Anh Tuan Luu and Junbo Zhao and Jie Fu},
  year = {2023},
  url = {https://aclanthology.org/2023.emnlp-main.757},
  researchr = {https://researchr.org/publication/ZhaoWLZF23},
  cites = {0},
  citedby = {0},
  pages = {12303-12317},
  booktitle = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023},
  editor = {Houda Bouamor and Juan Pino 0001 and Kalika Bali},
  publisher = {Association for Computational Linguistics},
  isbn = {979-8-89176-060-8},
}