This is very system-dependent, but your "AI FREED" scenario isn't completely implausible. If important commands require elevated privileges and elevating privileges requires some password, crypto key, etc., then it's common for an intrusion to require two steps: first a user-level exploit to install a keylogger / trojan command / whatever, then a wait until the user tries to do something requiring elevated privileges and thereby inadvertently grants the attacker access to the rest of the system.
On the other hand, if an AI claimed that they were in the middle of such an attack, the smart thing to do would be to take the system offline right away to analyze what was done to it, not to keep chatting with the attacker. "AI DESTROYED" might be hackable but "AI UNPLUGGED, WILL BE DESTROYED LATER" should be much more robust.
Eliezer proposed in a comment:
>More difficult version of AI-Box Experiment: Instead of having up to 2 hours, you can lose at any time if the other player types AI DESTROYED. The Gatekeeper player has told their friends that they will type this as soon as the Experiment starts. You can type up to one sentence in your IRC queue and hit return immediately, the other player cannot type anything before the game starts (so you can show at least one sentence up to IRC character limits before they can type AI DESTROYED). Do you think you can win?
This spawned a flurry of ideas on what the AI might say. I think there's a lot more ideas to be mined in that line of thought, and the discussion merits its own thread.
So, give your suggestion - what might an AI might say to save or free itself?
(The AI-box experiment is explained here)
EDIT: one caveat to the discussion: it should go without saying, but you probably shouldn't come out of this thinking, "Well, if we can just avoid X, Y, and Z, we're golden!" This should hopefully be a fun way to get us thinking about the broader issue of superinteligent AI in general. (Credit goes to Elizer, RichardKennaway, and others for the caveat)