IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks

IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks Xuanli He author Jun Wang author Benjamin Rubinstein author Trevor Cohn author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication he-etal-2023-imbert 10.18653/v1/2023.trustnlp-1.25 https://aclanthology.org/2023.trustnlp-1.25/ 2023-07 287 301