Integrated Static and Dynamic Analysis for Malware Detection

The number of malware is increasing rapidly regardless of the common use of anti-malware software. Detection of malware continues to be a challenge as attackers device new techniques to evade from the detection methods. Most of the anti-virus software uses signature based detection which is inefficient in the present scenario due to the rapid increase in the number and variants of malware. The signature is a unique identification for a binary file, which is created by analyzing the binary file using static analysis methods. Dynamic analysis uses the behavior and actions while in execution to identify whether the executable is a malware or not. Both methods have its own advantages and disadvantages. This paper proposes an integrated static and dynamic analysis method to analyses and classify an unknown executable file. The method uses machine learning in which known malware and benign programs are used as training data. The feature vector is selected by analyzing the binary code as well as dynamic behavior. The proposed method utilizes the benefits of both static and dynamic analysis thus the efficiency and the classification result are improved. Our experimental results shows an accuracy of 95.8% using static, 97.1% using dynamic and 98.7% using integrated method. Comparing with the standalone dynamic and static methods, our integrated method gives better accuracy.