<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Pan Jiahao 潘嘉灏 | Trustworthy AI Systems Lab (TAS Lab)</title><link>https://tas-lab.org/author/jiahao-pan/</link><atom:link href="https://tas-lab.org/author/jiahao-pan/index.xml" rel="self" type="application/rss+xml"/><description>Pan Jiahao 潘嘉灏</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><image><url>https://tas-lab.org/author/jiahao-pan/avatar_hu_8b2ce79e39f52ddd.jpg</url><title>Pan Jiahao 潘嘉灏</title><link>https://tas-lab.org/author/jiahao-pan/</link></image><item><title>Pan Jiahao 潘嘉灏</title><link>https://tas-lab.org/author/jiahao-pan/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://tas-lab.org/author/jiahao-pan/</guid><description>&lt;p&gt;Jiahao Pan is currently pursuing his degree at the Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, Guangzhou, China. His research interests broadly encompass deep learning and artificial intelligence security. He
has previously contributed to the field of remote sensing, with his research published in the prestigious IEEE Transactions on Geoscience and Remote Sensing. His current research focuses on adversarial attacks against Large Language Models (LLMs) and prompt engineering, with particular emphasis on developing structural adversarial frameworks for safety-aligned LLMs.&lt;/p&gt;</description></item></channel></rss>