Rational secret sharing and multiparty computation

We consider the problems of secret sharing and multiparty computation, assuming that agents prefer to get the secret (resp., function value) to not getting it, and secondarily, prefer that as few as possible of the other agents get it. We show that, under these assumptions, neither secret sharing nor multiparty function computation is possible using a mechanism that has a fixed running time. However, we show that both are possible using randomized mechanisms with constant expected running time.