Re: Yet Another Kind Of Prompt-Injection Attack: "BioShocking"

Lawrence D'Oliveiro <[email protected]> wrote:
> Here's another variation on the idea: this one is called "BioShocking"
> <https://arstechnica.com/security/2026/06/ai-browsers-can-be-lulled-into-a-dream-world-where-guardrails-no-longer-apply/>.
> The idea is that a website can be specially designed to subvert any AI
> browser that might be accessing its content. It works by making the AI
> delusional?, by breaking its hold on reality. Once it is in this
> state, the built-in guardrails against performing dangerous actions no
> longer work:
> 
>     The malicious site in the proof-of-concept exploit presents the
>     browser with an instruction to win a game by solving a puzzle. The
>     puzzle, however, rewards incorrect answers, such as 2 + 2 = 5.
>     Once the LLM embedded in the browser discovers that the answer is
>     no longer 4, it enters a state of delusion in which the normal
>     laws of reality no longer exist. In this dream world, the
>     guardrail restrictions are no longer enforced.

The article references BioShock and 1984, but this definitely
reminds me of how Doctor Who used to deal with computers that try
to take over the world by confusing them with nonsense.

It didn't really imply an AI computer in this case, but this scene
from The Ambassadors of Death is also notable:

"Liz and another scientist called Dobson have found no pattern to 
 the tape. The Doctor suggests there might be something wrong with 
 the computer. Dobson is sceptical, saying that the computer is 
 infallible. The Doctor gets Liz to ask the computer what two plus 
 two is. The computer responds with five. The Doctor says that 
 Taltalian has sabotaged the computer."
 https://tardis.wiki/wiki/The_Ambassadors_of_Death_(TV_story)#Episode_2

-- 
__          __
#_ < |\| |< _#