Gadi Evron · 2026 · arXiv
DOI: 10.48550/arXiv.2610.29379 · open-access PDF
基于LLM的漏洞发现可以错过真实的、可达到的漏洞,因为模型周围的是如何构建的。选择代码、过滤它、存储和合并发现的步骤可以在模型运行前或之后放下漏洞,而该模型的能力无关,报告通常不会显示这种情况的迹象。这些漏洞来自工程选择和错误。它们将漏洞留下未被检测,并且知道的规则的攻击者也可以使用它们来故意隐藏漏洞。
Machine translation (Meta M2M100); the English original follows.
LLM-based vulnerability discovery harnesses can miss real, reachable vulnerabilities because of how the harness around the model is built. Steps that select code, filter it, and store and merge findings can drop a vulnerability before or after the model runs, independently of the model's capability, and the report usually gives no sign that this happened. These drops come from engineering choices, and errors. They leave vulnerabilities undetected, and an attacker who knows the harness's rules can also use them to hide a vulnerability on purpose. Understanding these drops shows how to build har
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29379, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange