LinuxQuestions.org
Latest LQ Deal: Latest LQ Deals
Go Back   LinuxQuestions.org > Forums > Non-*NIX Forums > General
User Name
Password
General This forum is for non-technical general discussion which can include both Linux and non-Linux topics. Have fun!

Notices


Reply
  Search this Thread
Old 03-05-2024, 08:59 AM   #1
hazel
LQ Guru
 
Registered: Mar 2016
Location: Harrow, UK
Distribution: LFS, AntiX, Slackware
Posts: 7,543
Blog Entries: 19

Rep: Reputation: 4433Reputation: 4433Reputation: 4433Reputation: 4433Reputation: 4433Reputation: 4433Reputation: 4433Reputation: 4433Reputation: 4433Reputation: 4433Reputation: 4433
The first AI worm


This worm is only experimental but similar malware could be out in the wild in a couple of years. It infects intelligent email agents.
Quote:
To create the generative AI worm, the researchers turned to a so-called “adversarial self-replicating prompt.” This is a prompt that triggers the generative AI model to output, in its response, another prompt, the researchers say. In short, the AI system is told to produce a set of further instructions in its replies. This is broadly similar to traditional SQL injection and buffer overflow attacks, the researchers say.
To show how the worm can work, the researchers created an email system that could send and receive messages using generative AI, plugging into ChatGPT, Gemini, and open source LLM, LLaVA. They then found two ways to exploit the system—by using a text-based self-replicating prompt and by embedding a self-replicating prompt within an image file.
https://www.wired.com/story/here-come-the-ai-worms/
 
Old 03-05-2024, 09:16 AM   #2
rokytnji
LQ Veteran
 
Registered: Mar 2008
Location: Waaaaay out West Texas
Distribution: antiX 23, MX 23
Posts: 7,094
Blog Entries: 21

Rep: Reputation: 3473Reputation: 3473Reputation: 3473Reputation: 3473Reputation: 3473Reputation: 3473Reputation: 3473Reputation: 3473Reputation: 3473Reputation: 3473Reputation: 3473
So basically It tell you watch out of ai generated images on line while browsing. Watch out for sites using autofill.

I sure can't tell. Tell a LLM to act as a scammer. Gotta look that up also.

Quote:
by using a text-based self-replicating prompt and by embedding a self-replicating prompt within an image file.
Gotta readup on things like jail break.

I guess my best defence so far is I do not willy nilly autofill anything. Sounds dangerous.
Guess browser is attack region.
 
Old 03-07-2024, 09:45 AM   #3
mjolnir
Member
 
Registered: Apr 2003
Posts: 815

Rep: Reputation: 99
Thanks for the link, hazel. It was an interesting read.
 
  


Reply


Thread Tools Search this Thread
Search this Thread:

Advanced Search

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is Off
HTML code is Off



Similar Threads
Thread Thread Starter Forum Replies Last Post
Slaper worm FredrikN Linux - Security 5 09-17-2002 03:44 PM
Nimda worm virus becswhyte General 2 09-30-2001 05:04 PM
FYI - New worm: Nimda unSpawn Linux - Security 2 09-19-2001 07:15 PM
access_log full of junk, could it be code red worm? burger97 Linux - Security 8 08-13-2001 05:43 AM
Security Problem - New Worm tfrye Linux - Security 5 04-04-2001 08:41 AM

LinuxQuestions.org > Forums > Non-*NIX Forums > General

All times are GMT -5. The time now is 04:17 AM.

Main Menu
Advertisement
My LQ
Write for LQ
LinuxQuestions.org is looking for people interested in writing Editorials, Articles, Reviews, and more. If you'd like to contribute content, let us know.
Main Menu
Syndicate
RSS1  Latest Threads
RSS1  LQ News
Twitter: @linuxquestions
Open Source Consulting | Domain Registration