<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>AI보안 on WithinTrend — Trending Topics &amp; Guides</title><link>https://withintrend.org/tags/ai%EB%B3%B4%EC%95%88/</link><description>Recent content in AI보안 on WithinTrend — Trending Topics &amp; Guides</description><generator>Hugo -- 0.146.0</generator><language>ko-kr</language><lastBuildDate>Sat, 23 May 2026 05:58:16 +0900</lastBuildDate><atom:link href="https://withintrend.org/tags/ai%EB%B3%B4%EC%95%88/index.xml" rel="self" type="application/rss+xml"/><item><title>AI가 한 달 만에 보안 취약점 1만 개를 찾아냈다 — 이제 병목은 '고치는 속도'</title><link>https://withintrend.org/posts/2026-05-23-anthropic-glasswing-ai-finds-vulnerabilities/</link><pubDate>Sat, 23 May 2026 05:58:16 +0900</pubDate><guid>https://withintrend.org/posts/2026-05-23-anthropic-glasswing-ai-finds-vulnerabilities/</guid><description>Anthropic의 Project Glasswing 첫 경과 보고서. AI가 핵심 소프트웨어에서 1만 개 넘는 취약점을 찾아냈지만, 정작 문제는 그걸 검증하고 패치하는 속도였다.</description></item></channel></rss>