Document-borne AI worms can self-propagate through Copilot for Word
31–40 of 317 posts
Re: Document-borne AI worms can self-propagate through Copilot for Word
#32By the way, this is the method that uni professors have been using to catch students using LLMs to do homework. Paste any document in any LLM and you'll risk that, it's not something Microsoft specific.
Re: Document-borne AI worms can self-propagate through Copilot for Word
#33> Malicious instructions hidden in an externally shared document could make Copilot alter drafted or edited documents in Word and propagate the attack to new documents. Oh no.
Mixing instructions and data is never a good idea. And I thought people understood that.
Re: Document-borne AI worms can self-propagate through Copilot for Word
#34Earlier quoted context omitted.
Isn't React, the most popular JS library, an example of that? Clearly people don't understand that
No it’s not an example of that. Do you store components in your component state?
function Greeting({ name }) { return Hello, {name}; }
Re: Document-borne AI worms can self-propagate through Copilot for Word
#35> Malicious instructions hidden in an externally shared document could make Copilot alter drafted or edited documents in Word and propagate the attack to new documents. Oh no.
Mixing instructions and data is never a good idea. And I thought people understood that.
People get too hung up on this fundamentally wrong idea, and the space of security, instead of progressing, is just running in circles like a headless chicken, making a mess of everything.
Re: Document-borne AI worms can self-propagate through Copilot for Word
#36Re: Document-borne AI worms can self-propagate through Copilot for Word
#37I may be naive here but can the hidden text not be flagged or outright removed before being passed to copilot? Why would there not be consideration for what a human user can see, especially if the hidden text was added by copilot in the first place?
As long as Copilot can't be prevented from acting on instructions in its input, it would be safer to not make untrusted document content part of the input, similar to how macros in untrusted documents aren't executed by default.
Re: Document-borne AI worms can self-propagate through Copilot for Word
#38It's VBScript/macro worms all over again!
Re: Document-borne AI worms can self-propagate through Copilot for Word
#39Re: Document-borne AI worms can self-propagate through Copilot for Word
#40> Malicious instructions hidden in an externally shared document could make Copilot alter drafted or edited documents in Word and propagate the attack to new documents. Oh no.
- Erroneous information left in plain sight in an externally shared document could make Copilot - or any other agentic system, including LLMs and protein-based intelligence, alter drafted or edited documents in Word (or any other program, or with pen and paper) and propagate the errors to new documents.
In other news:
- Many humans still believe in silly superstitions like flat Earth or that code and data are fundamentally distinct, or that control vs. data plane is anything more than a design opinion that doesn't apply to the universe in general.