PulseAugur
实时 10:05:25
English(EN) Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection

大型语言模型在代码漏洞检测中易受认知偏差影响

一项新的研究论文探讨了与影响人类判断类似的认知启发式方法如何影响大型语言模型(LLMs)检测代码漏洞。研究发现,LLMs 容易受到光环效应、框架效应和锚定效应的影响,其中框架效应的影响最大,占 33.2%。这种易感性可能导致模型错误地将代码标记为易受攻击或安全,研究人员演示了一种黑盒攻击,该攻击可以抑制多达 97% 的已检测漏洞,凸显了基于 LLM 的安全工具中一个重要的可利用特性。 AI

影响 揭示了 LLM 安全工具中可利用的偏差,可能影响 AI 驱动的代码分析的可靠性。

排序理由 该集群包含一篇详细介绍 LLM 行为研究结果的论文。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

大型语言模型在代码漏洞检测中易受认知偏差影响

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Asif Shahriar, Hongyu Cai, Hadjer Benkraouda, Gang Wang, Z. Berkay Celik ·

    Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection

    arXiv:2606.30587v1 Announce Type: cross Abstract: Researchers and practitioners increasingly apply Large Language Models (LLMs) for automated vulnerability detection. Recent work has shown that LLMs are susceptible to the same cognitive heuristics that bias human judgment. Yet, n…

  2. arXiv cs.AI TIER_1 English(EN) · Z. Berkay Celik ·

    Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection

    Researchers and practitioners increasingly apply Large Language Models (LLMs) for automated vulnerability detection. Recent work has shown that LLMs are susceptible to the same cognitive heuristics that bias human judgment. Yet, no work has investigated whether these heuristics a…