PulseAugur
EN
LIVE 11:41:47
中文(ZH) 🌗 FFmpeg 中的 21 個零日漏洞 ➤ 透過 AI 代理進行低成本、高精準度的自主漏洞挖掘 ✤ https:// depthfirst.com/research/21-zer o-days-in-ffmpeg depthfirst 團隊透過自研的「自主安全代理」(Autonomous Security Agent

AI agent finds 21 zero-day vulnerabilities in FFmpeg at low cost

Depthfirst, a company specializing in AI-driven security, has announced its autonomous security agent has identified 21 zero-day vulnerabilities within the FFmpeg multimedia framework. This agent achieved this feat at a significantly lower cost compared to previous analyses by Google and Anthropic, costing approximately $1,000 versus $10,000. Notably, some of these vulnerabilities had remained undiscovered for up to 20 years, with the agent capable of generating reproducible proof-of-concept exploits. AI

IMPACT Demonstrates AI's potential to significantly reduce the cost and time for discovering critical software vulnerabilities.

RANK_REASON AI research paper detailing a new method for vulnerability discovery.

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

AI agent finds 21 zero-day vulnerabilities in FFmpeg at low cost

COVERAGE [2]

  1. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    "TLDR: depthfirst’s production autonomous security agent discovered 21 zero-day vulnerabilities in FFmpeg, after intensive security analysis by Google and Anthr

    "TLDR: depthfirst’s production autonomous security agent discovered 21 zero-day vulnerabilities in FFmpeg, after intensive security analysis by Google and Anthropic. Moving beyond theoretical analysis, our agent produces concrete, reproducible PoC inputs to confirm its findings a…

  2. Mastodon — mastodon.social TIER_1 中文(ZH) · GripNews ·

    21 Zero-Days in FFmpeg ➤ Low-Cost, High-Precision Autonomous Vulnerability Discovery via AI Agents ✤ https://depthfirst.com/research/21-zero-days-in-ffmpeg The Depth First team, through their self-developed "Autonomous Security Agent"

    🌗 FFmpeg 中的 21 個零日漏洞 ➤ 透過 AI 代理進行低成本、高精準度的自主漏洞挖掘 ✤ https:// depthfirst.com/research/21-zer o-days-in-ffmpeg depthfirst 團隊透過自研的「自主安全代理」(Autonomous Security Agent),成功在開源多媒體框架 FFmpeg 中挖掘出 21 個零日漏洞。相較於 Google 與 Anthropic 先前的研究,該團隊大幅降低了研發成本(僅約 1,000 美元),並確認了多項隱藏長達 23 年之久的安全性缺陷。該系統不僅能執…