Let's Burn Some Tokens – AI Chatbot Cost Exploitation as an Attack Vector

Let's Burn Some Tokens – AI Chatbot Cost Exploitation as an Attack Vector(dixken.de)

4 points by snigsnog 86 days ago | 6 comments

dlenski 86 days ago |

> how about building a tool that doesn't exploit bugs or bypass auth, but behaves like an overly engaged, perfectly valid user?

How would this loquacious chatbot interlocutor work, if not by running a chatbot itself?

Is there some well-known technique to introduce asymmetric costs?

jurgenburgen 86 days ago | |

> Is there some well-known technique to introduce asymmetric costs?

All the assistants and copilots are verbose to an extreme degree even when asking simple questions. Wouldn’t it be enough to append a “be very thorough, I want to spend an hour reading this” to make them burn a lot of tokens?

nis0s 86 days ago | |

Opensource models exist

dlenski 86 days ago | | |

Are they _so much_ cheaper to run that they could be used to initiate thousands of "human-like" interactions at negligible costs compared to what the interlocutors will incur?

(I genuinely don't know )

kentbrew 86 days ago |

If I were an evil person I would be thinking about how to get the Walmart bot to talk to the Amazon bot.