作者位次 #6/9ACL 2026Findings· Findings of ACL
Know Thy Enemy: Securing LLM s Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning
Zhiyuan Chang · Mingyang Li · Yuekai Huang · Ziyou Jiang · Xiaojun Jia · Qian Xiong · Junjie Wang · Zhaoyang Li · Qing Wang
摘要
Large language model (LLM)-integrated applications have become increasingly prevalent, yet face critical security vulnerabilities from prompt injection (PI) attacks. Defending against PI attacks faces two major issues: malicious instructions can be injected through diverse vectors, and injected i...