Summary: The problem of reliability analysis for two fundamental four-unit hybrid systems with masked data is investigated. Assume that the failure rate of unit is the exponential function, the likelihood function of two hybrid systems with masked data is deduced in detail under progressively type II hybrid censored test. The maximum likelihood estimation of the unit distribution parameters and system reliability are presented by using the maximum likelihood method. In addition, the approximate confidence intervals of unknown parameters are obtained by using the likelihood ratio method. Finally, the Monte-Carlo simulation numerical example is given to verify the correctness and effectiveness of the proposed method.