We study robust mechanisms to sell a common-value good.  We assume that the mechanism designer knows the prior distribution of the buyers' common value but is unsure about the buyers' information structure.  We use linear programming duality to derive mechanisms that guarantee a good revenue among all information structures and all equilibria.  When there are two buyers and a uniform [0, 1] distribution of common value, our mechanism guarantees a revenue of at least 0.27 for any information structure and any equilibrium, which is 0.27/0.5 = 54% of the best possible revenue.  When there is a single buyer, we obtain the optimal mechanism that maximizes the revenue guarantee among all information structures and all equilibria.