• Home
  • Ars
  • Man pleads guilty to using malicious AI software to hack Disney employee
https://cdn.arstechnica.net/wp-content/uploads/2021/03/getty-judge-gavel-1152x648.jpg

A California man has pleaded guilty to hacking an employee of The Walt Disney Company by tricking the person into running a malicious version of a widely used open source AI image-generation tool.

Ryan Mitchell Kramer, 25, pleaded guilty to one count of accessing a computer and obtaining information and one count of threatening to damage a protected computer, the US Attorney for the Central District of California said Monday. In a plea agreement, Kramer said he published an app on GitHub for creating AI-generated art. The program contained malicious code that gave access to computers that installed it. Kramer operated using the moniker NullBulge.

Not the ComfyUI you’re looking for

According to researchers at VPNMentor, the program Kramer used was ComfyUI_LLMVISION, which purported to be an extension for the legitimate ComfyUI image generator and had functions added to it for copying passwords, payment card data, and other sensitive information from machines that installed it. The fake extension then sent the data to a Discord server that Kramer operated. To better disguise the malicious code, it was folded into files that used the names OpenAI and Anthropic.

Read full article

Comments

Source Link: https://educronix.com/man-pleads-guilty-to-using-malicious-ai-software-to-hack-disney-employee/

Author: Ernestro Casas -

Published on:

This post was originally published on this site

Share this post

Subscribe to our newsletter

Keep up with the latest blog posts by staying updated. No spamming: we promise.
By clicking Sign Up you’re confirming that you agree with our Terms and Conditions.

Related posts