A statistical database (SDB) is a database that is used to provide statistical queries (such as sum, average). Sometimes, by stitching the answers of some statistics, a malicious user (snooper) may be able to deduce confidential information about some individuals. New auditing scheme is proposed to protect online and dynamic SDBs from being disclosed. The core idea is to convert the original database D into key representation database D\, namely sequence of particular values represent each corresponding record in the original database. Also this idea involves converting each new query q from string representation into key representation query q\, and stores it in the Audit Query table. Specific rules will be applied to decide whether the new user query could or couldn't lead to disclose the SDB. The proposed scheme that will be applied expected to guarantee the security of SDBs and provide precise and accurate responses, besides it need less CPU time and storage space during query processing. © 2008 IEEE.