<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Anusha Ghosh on The Trail of Bits Blog</title><link>https://miscreants.github.io/blog.trailofbits.com/authors/anusha-ghosh/</link><description>Recent content in Anusha Ghosh on The Trail of Bits Blog</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 15 Nov 2023 10:15:05 -0500</lastBuildDate><atom:link href="https://miscreants.github.io/blog.trailofbits.com/authors/anusha-ghosh/index.xml" rel="self" type="application/rss+xml"/><item><title>Assessing the security posture of a widely used vision model: YOLOv7</title><link>https://miscreants.github.io/blog.trailofbits.com/2023/11/15/assessing-the-security-posture-of-a-widely-used-vision-model-yolov7/</link><pubDate>Wed, 15 Nov 2023 10:15:05 -0500</pubDate><guid>https://miscreants.github.io/blog.trailofbits.com/2023/11/15/assessing-the-security-posture-of-a-widely-used-vision-model-yolov7/</guid><description>TL;DR: We identified 11 security vulnerabilities in YOLOv7, a popular computer vision framework, that could enable attacks including remote code execution (RCE), denial of service, and model differentials (where an attacker can trigger a model to perform differently in different contexts). Open-source software […]</description></item></channel></rss>