信息网络安全
大语言模型提示词注入攻击与防御综述
袁明, 邹其霖, 袁文骐, 王群
A Survey on Prompt Injection Attacks and Defenses in Large Language Models
YUAN Ming, ZOU Qilin, YUAN Wenqi, WANG Qun
信息网络安全 . 2026, (3): 341 -354 .  DOI: 10.3969/j.issn.1671-1122.2026.03.001