Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs

Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs Bibek Upadhayay author Vahid Behzadan author 2024-06 text Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024) Anaelia Ovalle editor Kai-Wei Chang editor Yang Trista Cao editor Ninareh Mehrabi editor Jieyu Zhao editor Aram Galstyan editor Jwala Dhamala editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Mexico City, Mexico conference publication upadhayay-behzadan-2024-sandwich 10.18653/v1/2024.trustnlp-1.18 https://aclanthology.org/2024.trustnlp-1.18/ 2024-06 208 226