@inproceedings{zeng-etal-2024-beear, title = "{BEEAR}: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models", author = "Zeng, Yi and Sun, Weiyu and Huynh, Tran and Song, Dawn and Li, Bo and Jia, Ruoxi", editor = "Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung", booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing", month = nov, year = "2024", address = "Miami, Florida, USA", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.emnlp-main.732/", doi = "10.18653/v1/2024.emnlp-main.732", pages = "13189--13215" }