<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Kikimora Morozova on The Trail of Bits Blog</title><link>https://miscreants.github.io/blog.trailofbits.com/authors/kikimora-morozova/</link><description>Recent content in Kikimora Morozova on The Trail of Bits Blog</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 21 Aug 2025 00:00:00 -0400</lastBuildDate><atom:link href="https://miscreants.github.io/blog.trailofbits.com/authors/kikimora-morozova/index.xml" rel="self" type="application/rss+xml"/><item><title>Weaponizing image scaling against production AI systems</title><link>https://miscreants.github.io/blog.trailofbits.com/2025/08/21/weaponizing-image-scaling-against-production-ai-systems/</link><pubDate>Thu, 21 Aug 2025 07:00:00 -0400</pubDate><guid>https://miscreants.github.io/blog.trailofbits.com/2025/08/21/weaponizing-image-scaling-against-production-ai-systems/</guid><description>In this blog post, we’ll detail how attackers can exploit image scaling on Gemini CLI, Vertex AI Studio, Gemini’s web and API interfaces, Google Assistant, Genspark, and other production AI systems. We’ll also explain how to mitigate and defend against these attacks, and we’ll introduce Anamorpher, our open-source tool that lets you explore and generate these crafted images.</description></item></channel></rss>