arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.01154cs.CR
收藏

vEcho:从漏洞验证到大语言模型主动发现的范式转变

vEcho: A Paradigm Shift from Vulnerability Verification to Proactive Discovery with Large Language Models

Southeast University(东南大学);Anhui University(安徽大学);Anhui Shenwu Information Technology Co., Ltd.(安徽神武信息技术有限公司)

Mingcheng Jiang, Jiancheng Huang, Jiangfei Wang, Zhengzhu Xie, Nan Fang, Guang Cheng, Xiaoyan Hu, Hua Wu

AI总结:

vEcho利用大语言模型主动发现漏洞,显著提升检测率并降低误报率,同时发现新的0日漏洞。

摘要:

静态应用程序安全测试(SAST)工具常常面临较高的误报率,导致警报疲劳,消耗了宝贵的审计资源。最近利用大语言模型(LLMs)作为过滤器的努力提供了有限的改进;然而,这些方法将LLMs视为被动的、无状态的分类器,缺乏项目层面的上下文和从分析中学习的能力,无法发现未知的、相似的漏洞。在本文中,我们提出vEcho,一种新的框架,将LLM从被动过滤器转变为能够学习、记忆和推理的虚拟安全专家。vEcho为其核心推理引擎配备了强大的开发者工具套件,用于深入的、上下文感知的验证。更重要的是,我们引入了一种新的回声漏洞传播(EVP)机制。由模拟人类学习的认知记忆模块驱动,EVP使vEcho能够从已验证的漏洞中学习,并主动推断未知的、相似的缺陷,实现了从被动验证到主动发现的范式转变。在CWE-Bench-Java数据集上的广泛实验表明,vEcho在双重优势上优于最先进的基线模型IRIS。具体而言,vEcho的检测率达到65%,比IRIS的45.83%高出41.8%。至关重要的是,它同时通过将误报率降至59.78%来解决警报疲劳问题,比IRIS的84.82%减少了28.3%。此外,vEcho在开源项目中主动发现了51个新的0日漏洞,除了数据集中记录的120个已知漏洞外,还发现了37个额外的已知漏洞。

英文摘要:

Static Application Security Testing (SAST) tools often suffer from high false positive rates, leading to alert fatigue that consumes valuable auditing resources. Recent efforts leveraging Large Language Models (LLMs) as filters offer limited improvements; however, these methods treat LLMs as passive, stateless classifiers, which lack project-wide context and the ability to learn from analyses to discover unknown, similar vulnerabilities. In this paper, we propose vEcho, a novel framework that transforms the LLM from a passive filter into a virtual security expert capable of learning, memory, and reasoning. vEcho equips its core reasoning engine with a robust developer tool suite for deep, context-aware verification. More importantly, we introduce a novel Echoic Vulnerability Propagation (EVP) mechanism. Driven by a Cognitive Memory Module that simulates human learning, EVP enables vEcho to learn from verified vulnerabilities and proactively infer unknown, analogous flaws, achieving a paradigm shift from passive verification to active discovery. Extensive experiments on the CWE-Bench-Java dataset demonstrate vEcho's dual advantages over the state-of-the-art baseline, IRIS. Specifically, vEcho achieves a 65% detection rate, marking a 41.8% relative improvement over IRIS's 45.83%. Crucially, it simultaneously addresses alert fatigue by reducing the false positive rate to 59.78%, a 28.3% relative reduction from IRIS's 84.82%. Furthermore, vEcho proactively identified 37 additional known vulnerabilities beyond the 120 documented in the dataset, and has discovered 51 novel 0-day vulnerabilities in open-source projects.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑