研究人员发现了一种大型语言模型（LLM）的新漏洞，其中一种旨在提高代码生成可靠性的技术——语法约束解码（GCD），可能被利用来生成恶意代码。这种名为CodeSpear的攻击利用良性代码语法约束来绕过LLM的安全措施。为了应对这一威胁，研究人员开发了一种名为CodeShield的新防御机制，该机制通过训练LLM在GCD下生成无害的“蜜罐”代码，从而在不牺牲实用性的情况下保持安全性。 AI
影响 新的攻击向量凸显了LLM代码生成中的安全风险，需要CodeShield等强大的防御措施。
排序理由 该集群包含一篇学术论文，详细介绍了LLM的新漏洞和防御机制。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2606.11817v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code. Meanwhile, Grammar-Constrained Decoding (GCD) has been widely adopted to improve the reli…
Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code. Meanwhile, Grammar-Constrained Decoding (GCD) has been widely adopted to improve the reliability of LLM-generated code by enforcing syntact…
Grammar-constrained decoding techniques used to ensure syntactic validity in code generation can be exploited as an attack surface, leading to the development of a jailbreak method called CodeSpear and a safety alignment approach named CodeShield.