<?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>对抗样本 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E5%AF%B9%E6%8A%97%E6%A0%B7%E6%9C%AC/</link><description>Recent content in 对抗样本 on 硅基 AGI · 智能体学习与测评</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Thu, 02 Jul 2026 10:32:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%AF%B9%E6%8A%97%E6%A0%B7%E6%9C%AC/index.xml" rel="self" type="application/rss+xml"/><item><title>对抗攻击与LLM：大语言模型的对抗鲁棒性研究</title><link>https://guijiagi.com/posts/adversarial-attacks-llm/</link><pubDate>Thu, 02 Jul 2026 10:32:00 +0800</pubDate><guid>https://guijiagi.com/posts/adversarial-attacks-llm/</guid><description>深入探讨大语言模型面临的对抗攻击手法与鲁棒性提升策略</description></item><item><title>越狱技术目录与防御：AI安全攻防全景</title><link>https://guijiagi.com/posts/jailbreak-techniques-catalog/</link><pubDate>Thu, 02 Jul 2026 10:21:00 +0800</pubDate><guid>https://guijiagi.com/posts/jailbreak-techniques-catalog/</guid><description>系统梳理2026年主流越狱技术手法与对应的防御策略，为AI安全从业者提供全景参考</description></item></channel></rss>