期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2017
卷号：95
期号：10
出版社：Journal of Theoretical and Applied
摘要：One of the critical factor of computer aided services and data security is defending malicious executables known as malwares. Since the zero day activities of malware, it becomes continuous process to sense and prevent the malicious activities of the vulnerable executables. The contemporary literature evinces the many of malware detection approaches. The malware detection by dynamic assessment is figured as significant to explore the behavioral information of the malicious executables. The recent malware analysis is concluding that the act of obfuscating the malicious executables is boosting the complexity of defending such attacks. This practice strongly demanding the more accurate malware defending approaches, hence this manuscript contributed an exploratory scale to analyze API call sequence in order to estimate the scope of malicious act by an executable. The proposed model called Exploratory Scale for Malware Perception (ESMP) is a machine learning strategy that acquires knowledge from the defined executables that labeled as either malicious or benevolent. Further this knowledge is used to define the exploratory scale proposed. ESMP even capable of identifying zero day exploiting of malware. The experimental study was carried out on set of executables labeled as either malicious or benevolent. The 70% of the given executables were used to train the ESMP to define exploratory scale and rest 30% were unlabeled and given to test the significance of the ESMP towards malware detection accuracy. The statistical metrics such as accuracy, sensitivity and specificity were assessed to notify the scalability, robustness and detection accuracy of the ESMP.
关键词：Executables; Malwares; Benevolent; Zero day activities; Exploratory.
