<?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>AIDefense on TechLLM</title><link>https://techllm.github.io/tags/aidefense/</link><description>Recent content in AIDefense on TechLLM</description><generator>Hugo</generator><language>ko</language><lastBuildDate>Thu, 30 Apr 2026 19:30:00 +0900</lastBuildDate><atom:link href="https://techllm.github.io/tags/aidefense/index.xml" rel="self" type="application/rss+xml"/><item><title>OpenAI GPT-5.5-Cyber, 왜 제한 공개로 시작하나</title><link>https://techllm.github.io/posts/openai-gpt-55-cyber-critical-defenders/</link><pubDate>Thu, 30 Apr 2026 19:30:00 +0900</pubDate><guid>https://techllm.github.io/posts/openai-gpt-55-cyber-critical-defenders/</guid><description>OpenAI가 보안 방어자를 위한 GPT-5.5-Cyber를 제한 공개한다는 소식과 그 의미를 정리한다.</description></item></channel></rss>