大模型对齐与安全

AEGIS : Automated Co-Evolutionary Framework for Guarding Prompt Injections Schema

Ting-Chun Liu, Ching-Yu Hsu, Kuan-Yi Lee, Chi-An Fu, Hung-yi Lee

机构 * Electrical Engineering, National Taiwan University（国家台湾大学电子工程系） 纠错

专题命中 提示注入 ：prompt injection(title,abstract)；分类 cs.AI、cs.LG

Rule Encoding and Compliance in Large Language Models: An Information-Theoretic Analysis

Joachim Diederich

专题命中 提示注入 ：safety(abstract)；prompt injection(abstract)；分类 cs.AI