PulseAugur
实时 10:38:47
English(EN) VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities

新基准VEX-Bench测试LLM代理对软件供应链漏洞可利用性的评估能力

研究人员推出了VEX-Bench,这是首个旨在评估大型语言模型(LLM)代理评估软件供应链漏洞可利用性能力的基准测试。该基准包含75个来自GitHub的真实案例,并经过安全专家验证,涵盖Python、Java和Go编程语言。初步评估显示,尽管GPT-5.5和Claude Opus-4.6等模型在二进制漏洞状态分类方面取得了约80%的F1分数,但GPT-5.5在细粒度理由分类方面表现更优,凸显了超越简单可利用性评估的难度。 AI

影响 该基准测试有望加速更复杂的网络安全LLM代理的开发,提高软件供应链漏洞评估的效率。

排序理由 该集群描述了一个用于评估LLM代理在特定任务上表现的新学术基准测试,该测试在一篇研究论文中发布。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新基准VEX-Bench测试LLM代理对软件供应链漏洞可利用性的评估能力

本文如何被排名

Signal score
10 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群描述了一个用于评估LLM代理在特定任务上表现的新学术基准测试,该测试在一篇研究论文中发布。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Jiahao Shi, Edward Tsien, Yifeng Di, Hongjiao Zhang, Yuan Tang, Ronit Dey, Ilona Shishov, Gal Netanel, Zvi Grinberg, Vladimir Belousov, Bat-Zion Rotman, Ilan Pinto, Tianyi Zhang ·

    VEX-Bench:用于评估软件供应链漏洞可利用性的 LLM Agent 基准测试

    arXiv:2609.08040v1 Announce Type: cross Abstract: The software supply chain has become an increasingly exposed attack surface because of its reliance on intricate yet fragile dependencies. Existing defenses such as GitHub Dependabot often raise many false alerts because their coa…