<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>M. Chaudhary | TSG Lab – Technical Safety &amp; Governance Lab</title><link>https://tsglab.github.io/author/m.-chaudhary/</link><atom:link href="https://tsglab.github.io/author/m.-chaudhary/index.xml" rel="self" type="application/rss+xml"/><description>M. Chaudhary</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Thu, 01 May 2025 00:00:00 +0000</lastBuildDate><image><url>https://tsglab.github.io/media/logo.svg</url><title>M. Chaudhary</title><link>https://tsglab.github.io/author/m.-chaudhary/</link></image><item><title>SafetyNet: Detecting Harmful Outputs in LLMs by Modeling and Monitoring Deceptive Behaviors</title><link>https://tsglab.github.io/publication/safetynet-deceptive-behaviors/</link><pubDate>Thu, 01 May 2025 00:00:00 +0000</pubDate><guid>https://tsglab.github.io/publication/safetynet-deceptive-behaviors/</guid><description/></item></channel></rss>