Can LLMs deeply detect complex malicious queries? A framework for jailbreaking via obfuscating intent

Open Webpage

Shang Shang, Xinqiang Zhao, Zhongjiang Yao, Yepeng Yao, Liya Su, Zijing Fan, Xiaodan Zhang, Zhengwei Jiang

Published: 2025, Last Modified: 07 Jan 2026Comput. J. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0