一作ACL 2026Findings· Findings of ACL
M ulti C ode A ttack: Iterative Jailbreak Attacking on LLM s with Multi-Code Prompt Injection
Weifeng Sun · Meng Yan · Zhou Yang · Yuchen Chen · Song Sun · David Lo
摘要
Large Language Models (LLMs) demonstrate strong generalization capabilities but remain vulnerable to jailbreak attacks that induce restricted text or malicious code generation.Recent structured jailbreaks embed adversarial intent into code-like templates and have demonstrated promising effectiven...