This paper is concerned the robust stability analysis problem for uncertain stochastic neural networks with interval time-varying delays. By utilizing a Lyapunov functional and conducting stochastic analysis, we show that the addressed neural networks are globally, robustly, asymptotically stable if a convex optimization problem is feasible. A stability criterion is derived such that for all admissible uncertainties. And the stability criterion is formulated by means of the feasibility of a linear matrix inequality (LMI), which can be effectively solved by some standard numerical packages. A numerical example is given to demonstrate the usefulness of the proposed robust stability criterion.