alt Hacker NewsThere is literally no protection or difference of an opensource model doing this.
An actual objection I had while talking to an aerospace company was they don't want opensource models because the threat of it having a poisoned training example on specific systems.
It's easily the most hidden malware possible, completely undetectable until an exact set of tokens unlocks it. Is it line 100,543 of your security product? You will literally not know until it plants it in there.
Replies
To the best of my knowledge (which, admittedly, is far from comprehensive), that kind of attack on a model shouldn't actually be possible in a deterministic fashion.
If you can't stop them from sometimes telling customers things like "yes, I will give you a penthouse suite at our hotel for only $3/night", why would you be able to guarantee that, with some specific set of tokens, they would produce a perfect and undetectable backdoor customized to the code at hand?
You can review generated code manually or with models from a second vendor (ideally from a different country). Attackers would have to poison both and do it in a way that also makes them ignore the planted malware when reading code.
Open models also let you read reasoning traces. That means anomalies would show up when the backdoor activates, like a run of unrelated words or a jump in top token probability. It's only undetectable until the first time it happens.