*Result*: Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities
*Title*:
Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities / Jiahui Geng, Thy Thy Tran, Preslav Nakov, Iryna Gurevych
*Author/editor-in-chief*:
*Published in*:
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics. Volume 1 Long Papers. - Band 1, Heft /p2917–2933 (2025)
*Manufacture*:
2025
*Format*:
*Language*:
*eng*
*Subject Added Keywords*:
*DOI*:
10.18653/v1/2025.acl-long.146
*oa_rights*:
Open Access
CC BY 4.0
CC BY 4.0