PulseAugur
中
实时 07:03:57
English(EN) FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMs

新基准FuzzingBrain-Bench V1测试LLM的开放式漏洞发现能力

作者 PulseAugur 编辑部 · [1 个来源] ·

研究人员推出了FuzzingBrain-Bench V1，这是一个旨在评估大型语言模型（LLM）开放式漏洞发现能力的新基准。与专注于触发预定义漏洞的先前基准不同，FuzzingBrain-Bench V1挑战模型在Docker化环境中在开源软件中找到尽可能多的不同崩溃。该基准包含43个项目中的77个挑战，重点关注C、C++和Java/JVM代码。在评估中，Claude Opus 4.8表现最强，成功触发了77个挑战中的60个崩溃。 AI

影响 该基准可能有助于对LLM在软件安全性和可靠性方面进行更严格的评估。

排序理由 该集群描述了一个用于评估LLM的新学术基准。[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FuzzingBrain-Bench V1测试LLM的开放式漏洞发现能力

本文如何被排名

Signal score
25 / 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的新学术基准。[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
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

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) · Ze Sheng, Aleksandar Kezic, Zhicheng Chen, Jeff Huang ·

    FuzzingBrain-Bench V1: 评估LLM开放式漏洞发现能力

    arXiv:2608.25158v1 Announce Type: cross Abstract: Evaluating the ability of large language models (LLMs) to discover software bugs is increasingly important. Existing benchmarks typically evaluate this capability by asking the model to generate a proof-of-concept input that trigg…

相关实体

相关话题