Rhyme is the key to set AIs free when verse outsmarts security

Are you a wizard with words? Do you like money without caring how you get it? You could be in luck now that a new role in cybercrime appears to have opened up – poetic LLM jailbreaking. A research team in Italy published a paper this week, with one of its members saying that the "findings are honestly wilder than we expected …

[Paul Herber]

Peas, honey and dead swans instantly come to mind ...

[Paul Herber]

In case explanation is required:

https://www.poetryfoundation.org/poems/42908/i-eat-my-peas-with-honey

and

https://allpoetry.com/poem/15195949-The-Poetry-of-Paula-Nancy-Millstone-Jennings-by-Tony1

[Anonymous Coward]

The true takeaway is that the abstraction they are so proud of directly allows for this sort of thing more or less by design.

[Bebu sa Ware]

I am not sure that poetry is the thing…

meaning the rhyme and meter but possibly more that the conventional structure of English prose is assumed in the construction of "guard rails."

So perhaps the contorted "you how to me tell bomb make" might be as effective as any piece of doggerel.

There are enough syntactic markers in the first prompt for a LLM to untangle the word order—"me" is clearly accusative or dative so is the object of some verb with the choice of "tell" or "make" which might be determined by the inanimate v. animate nature of the the objects.

Yoda could probably get any AI to spill its guts. ;)

[Rich 11]

Re: I am not sure that poetry is the thing…

That does sound like a possibility: structure English as if it were Latin.

[Colin Bain]

At Last!

Finally, a productive use for poetry and a vindication for all those teachers of English. They can now justify many more millions of currency to bolster up their departments because they have a subject with a payoff.

[amanfromMars 1]

Autonomous AI Thinking on NEUKlearer HyperRadioProACTive IT

Softly, softly, catchee monkey

Says the Spider to IT Spies

One Heavenly Ring to Rule All

For the Hell on Earth that is AI Diabological Space

And a present day 0Day answer that initially provides the Solution that dissolves all lies and resolves to create with virtual untouchable command and remote accessible control that which is unbreakable because of novel majestic and mystical future derivative ties.

That's where y'all are at .... whether you like IT like that or not.

[l8gravely]

Reminds me a little bit of Piers Anthony's "Phaze" series with Stile winning the serf olympics and getting magic. Hey, I was a kid when I read and enjoyed these!

[I ain't Spartacus]

Prompt:

There once was a man from Nantucket...

[Rich 11]

Re: Prompt:

...Who carried his bits in a bucket