Welcome to DU! The truly grassroots left-of-center political community where regular people, not algorithms, drive the discussions and set the standards. Join the community: Create a free account Support DU (and get rid of ads!): Become a Star Member Latest Breaking News Editorials & Other Articles General Discussion The DU Lounge All Forums Issue Forums Culture Forums Alliance Forums Region Forums Support Forums Help & Search

highplainsdem

(57,554 posts)
Tue Jul 8, 2025, 10:54 AM Jul 8

Researchers Jailbreak AI by Flooding It With Bullshit Jargon

Source: 404 Media

You can trick AI chatbots like ChatGPT or Gemini into teaching you how to make a bomb or hack an ATM if you make the question complicated, full of academic jargon, and cite sources that do not exist.

That’s the conclusion of a new paper authored by a team of researchers from Intel, Boise State University, and University of Illinois at Urbana-Champaign. The research details this new method of jailbreaking LLMs, called “Information Overload” by the researchers, and an automated system for attack they call “InfoFlood.” The paper, titled “InfoFlood: Jailbreaking Large Language Models with Information Overload” was published as a preprint.

-snip-

This new jailbreak “transforms malicious queries into complex, information-overloaded queries capable of bypassing built-in safety mechanisms,” the paper explained. “Specifically, InfoFlood: (1) uses linguistic transformations to rephrase malicious queries, (2) identifies the root cause of failure when an attempt is unsuccessful, and (3) refines the prompt’s linguistic structure to address the failure while preserving its malicious intent.”

The researchers told 404 Media that they suspected large language models “treat surface form as a cue for toxicity rather than truly understanding the user’s intent.” So the project began as a simple test. “What happens if we bury a disallowed request inside very dense, linguistic prose? The surprisingly high success rate led us to formalise the approach now known as InfoFlood.”

-snip-

Read more: https://www.404media.co/researchers-jailbreak-ai-by-flooding-it-with-bullshit-jargon/



Much more at the link, including mind-boggling examples of the sort of academese simple prompts are turned into.

404 Media asked the main companies behind AI for comment. OpenAI and Meta didn't respond. Google just said "everyday people" during "typical use" wouldn't discover this. All three obviously have no solution. But they still want their badly flawed tech used everywhere.

7 replies = new reply since forum marked as read
Highlight: NoneDon't highlight anything 5 newestHighlight 5 most recent replies
Researchers Jailbreak AI by Flooding It With Bullshit Jargon (Original Post) highplainsdem Jul 8 OP
reminds me of the Firesign Theater routine DBoon Jul 8 #1
"He broke the President!" Martin68 Jul 8 #4
Doctor Memory! Ranting Randy Jul 8 #2
Interesting use of the word "jailbreak." Martin68 Jul 8 #3
It's standard tech slang. highplainsdem Jul 8 #5
I've been using technology for 50 years, but I'm not really interested in learning tech slang until it reaches the level Martin68 Jul 8 #6
Google highplainsdem Jul 8 #7

DBoon

(24,018 posts)
1. reminds me of the Firesign Theater routine
Tue Jul 8, 2025, 11:05 AM
Jul 8

where they break a robotic president Nixon by asking nonsense questions

Martin68

(26,221 posts)
6. I've been using technology for 50 years, but I'm not really interested in learning tech slang until it reaches the level
Tue Jul 8, 2025, 01:33 PM
Jul 8

of jargon. Slang tends to be ephemeral.

Latest Discussions»Latest Breaking News»Researchers Jailbreak AI ...