Now-a-days it is common to share data between two organizations in many application areas. When data are to be shared between parties, there could be some sensitive patterns which should not be disclosed to the other parties. We address such the problem of sensitive classification rule hiding. We propose a blocking based approach for sensitive classification rule hiding. First we find the supporting transactions of sensitive rules. Then we replace known values with unknown values ("?") in those transactions to hide a given sensitive classification rule. Finally the sanitized dataset is generated from which sensitive classification rules are no longer mined. We also discuss experimental results of our algorithm.