Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding

Seongho Joo, Hyukhun Koh, Kyomin Jung. Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding. In Christos Christodoulopoulos 0001, Tanmoy Chakraborty 0002, Carolyn Rose, Violet Peng, editors, Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025, Suzhou, China, November 4-9, 2025. pages 25489-25524, Association for Computational Linguistics, 2025. [doi]

Authors

Seongho Joo

This author has not been identified. Look up 'Seongho Joo' in Google

Hyukhun Koh

This author has not been identified. Look up 'Hyukhun Koh' in Google

Kyomin Jung

This author has not been identified. Look up 'Kyomin Jung' in Google