@article{beearembeddingbasedadversarialremovalof, title = {BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models}, author = {Yi Zeng and Weiyu Sun and Tran Ngoc Huynh and Dawn Song and Bo Li and Ruoxi Jia}, year = {2024}, eprint = {2406.17092}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.17092v1}, }