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.
In this context “secure AI” has the connotations of being well-protected against hackers.
I think that “secure” generally has the connotations of being secure against external threats. A “secure facility” is one into which outsiders cannot get into, but it may well contain nuclear bombs.
In this context “secure AI” has the connotations of being well-protected against hackers.
Well, that should be a necessary if not sufficient condition. Do you think it would dominate other interpretations to laymen/nonexperts?
I think that “secure” generally has the connotations of being secure against external threats. A “secure facility” is one into which outsiders cannot get into, but it may well contain nuclear bombs.