Computer security might be a good metaphor, at least in some contexts (particularly institutional contexts). Secure AI or Human-Secure AI gets across the general quality of high stakes with more appropriate connotations than High-Assurance and less impossible.

It also has the bonus that it draws an implicit connection to mathematical security, since insofar as we can say anything about eventual implementation of a Friendly/Safe/Secure AGI, it's fair to say that it's extremely likely to rely on advances descending from current techniques in provably-secure computing. Also the bonus that talking up security is frequently a good way to get Organizations With Money to start reaching for their wallets.