@seclink: google 认为 光靠 大模型自身来做漏洞挖掘是不够的, 关键还是要结合 harness ...

X AI KOLs Following 新闻

摘要

Google指出,在漏洞挖掘中仅依赖大型语言模型是不够的,关键需结合代理式漏洞发现框架,例如其团队利用该工具在短时间内发现多个关键漏洞。

google 认为 光靠 大模型自身来做漏洞挖掘是不够的, 关键还是要结合 harness ...
查看原文
查看缓存全文

缓存时间: 2026/08/19 22:53

google 认为 光靠 大模型自身来做漏洞挖掘是不够的, 关键还是要结合 harness …

J4X (@J4X_Security): Google just shared some results from their agentic vulnerability discovery harness.

In one engagement it found 100+ true positive critical vulnerabilities in 2 days (googles numbers).

But I think the approach they use is more interesting than the number itself.

Instead of

相似文章

@MaxForAI: 刚刚,一篇可能会引起大模型圈地震的论文发表了! 研究人员第一次系统性地从 OpenAI、Anthropic、Google 的闭源模型里,大规模“偷”出了真正的隐藏思维链。 然后,他们顺手拿这些思维链去研究了 Kimi K3、GLM-5.2…

X AI KOLs Timeline

研究人员首次系统性地从OpenAI、Anthropic、Google的闭源模型中提取隐藏思维链,利用API加密兼容漏洞让较弱模型解密,从而绕过CoT蒸馏防护,并研究了Kimi K3、GLM-5.2、DeepSeek等开源模型。

@AdamShao: 正式开源我的漏洞挖掘工具:http://flounders.xyz 这是一个基于 AI Agent 的全自动漏洞挖掘工作流,你只要告诉 AI 你要找什么项目的漏洞,它就会自动下载代码和文档,深度审计代码,发现可疑漏洞,自动在本地和线上验证…

X AI KOLs Timeline

Flounder is an open-source AI agent-based tool that automates vulnerability discovery in codebases. Users describe the target and the tool autonomously downloads code, conducts deep code audits, tests vulnerabilities locally and online, and generates reports.

@apivixtls: 这篇文章看完后,我真正注意到的点不是比哪个模型更厉害。作者拿AI跑了一圈实际的安全研究测试。Semgrep直接没找到。Strix接GLM 5.1跑了12小时,花了接近6000万tokens,还是没抓到关键漏洞。Cursor配GPT 5.5…

X AI KOLs Timeline

A security researcher tested four AI approaches (Semgrep, GLM 5.1+Strix, Cursor+GPT 5.5, local AI with custom harness) to find a known LFI vulnerability in PHPIPAM. Only the local AI harness consistently succeeded, demonstrating that the harness methodology matters more than the model, and highlighting advantages of local AI for cost, privacy, and flexibility in security research.