Nowadays computer systems and communication infrastructures are likely to be influenced by different types of attacks so there is need to put further efforts for improving the software trust. Therefore, there will be increase in necessity in the coming time, as the number of software developers and applications will likely grow very significantly. As important advances have been already made on malware executables detection in personal computers in the previous decades which we have reviewed in previous works. However there is more need to adopt some better techniques which can ensure the malware code detection efficiently by testing method over a large set of malicious executables. This paper explores the application of data mining methods to predict rootkits based on the attributes extracted from the information contained in the log files. The rootkit records were categorized as Inline and Other based on the attribute values. In this paper, we proposed three algorithms named as RIPPER, Naives Bayes approach, and Multi-Naïve Bayes using data mining techniques and the comparison of these algorithms.