The security of SNOW 2.0-like stream ciphers against a wide class of correlation attacks can be evaluated by values of some numerical parameters of s-boxes used in these ciphers. We propose a fast algorithm that computes the values of these parameters. The proposed algorithm is based on the fast Hadamard transform and has significantly lower time complexity compared to the previously known ones. We also show experimentally, using the Monte Carlo method, that for most random 8 x 8 s-boxes the values of the considered parameters ensure an appropriate security level of SNOW 2.0-like stream ciphers against known correlation attacks.