新研究表明，虽然先进的提示技术可以影响 AI 生成代码中存在的安全漏洞的类型，但它们并不能可靠地减少这些问题的总体数量或严重性。对多种编程语言的多个 LLM 进行的评估研究发现，生成的代码经常包含关键漏洞，例如弱加密和不当的输入验证。虽然一些方法改变了常见漏洞枚举 (CWE) 的分布，但它们并未消除固有风险，这表明仅靠提示工程不足以确保安全的代码生成。 AI
影响 LLM 生成代码的先进提示技术并不能可靠地减少漏洞，这凸显了除了提示工程之外，还需要更强大的安全措施。
排序理由 arXiv 上发表的多篇学术论文提出了用于改进 LLM 生成代码安全性的实证评估和新框架。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2605.24298v1 Announce Type: cross Abstract: The growing use of Large Language Models (LLMs) for automated code generation has enhanced software development efficiency, but often at the cost of security. Generated code frequently overlooks critical concerns, leaving it vulne…
arXiv:2605.24300v1 Announce Type: cross Abstract: Large language models (LLMs) are widely used for code generation, but their security reliability remains inconsistent across languages and prompting strategies. Existing prompt engineering improves functional correctness but rarel…
arXiv:2601.06366v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are transforming enterprise workflows but introduce security and ethics challenges when employees inadvertently share confidential data or generate policy-violating content. This paper proposes…
arXiv:2605.23091v1 Announce Type: cross Abstract: The majority of software developers use or are planning to use Artificial Intelligence (AI) tools in their development processes. Their top reasons include improving productivity and faster learning. In fact, Large Language Model …