@article{MAKHILLRJAS201611109869,
    title = {Review of Data Mining Techniques for Malicious Detection},
    journal = {Research Journal of Applied Sciences},
    volume = {11},
    number = {10},
    pages = {942-947},
    year = {2016},
    issn = {1815-932x},
    doi = {rjasci.2016.942.947},
    url = {https://makhillpublications.co/view-article.php?issn=1815-932x&doi=rjasci.2016.942.947},
    author = {Nawfal Turki and},
    keywords = {Malicious code,malicious detection,API calls,data mining},
    abstract = {Malicious is the term used to illustrate any code in any part of a software system that is expected to bring about undesired impacts, security breaks or harm to a system. Malicious programming is outlined with a hurtful intent. Recently, malicious detectors attempt to distinguish unwanted codes by checking Application Programming Interface (API) calls using data mining techniques and/or different methods. Matching the API call utilizing data mining strategies can be utilized as a part of malicious detection systems, for example, frequent pattern, clustering, etc. In this study, a review of malicious detection system based on API calls and data mining strategies are taking into account. Each malicious sample is represented as a data of API calls to the data mining techniques. After transforming the sample that input as a simplified data based on data mining techniques, data mining matching calculations are utilized to similarity between the data tested sample and malicious API call tested samples placed in a database. In this study, a review of utilization of various data mining methods for the detection of malicious program.}
    }