Web application scanning for malware attack detection with provide appropriate incident report by using hybrid method

Nowadays, antivirus software is one of the ways to measure the increasing number of malware not only on the computer but also on the information system as well as the software that needs to be protected from any attacks. The malware detection process becomes a challenge because the attacker has a new technique to penetrate it. Most anti-virus software uses unmatched signatures to prevent the increase in the number of malware variants. Signature is a unique confirmation for binary files. It is created by binary file analyzer using static analysis method. In addition, the next analysis is known as the dynamic analysis that requires behavior and action during execution to identify whether it can be malware or not. Both methods have their own advantages and disadvantages. This project proposes a static and dynamic analysis method of combining to produce a method known as hybrid. It will analyze as well as classify files vulnerable to unknown malware. Additionally, in order to create this method, it is necessary to use a machine learning where a malware program is used as a data set. Feature vectors have been selected by analyzing binary code and dynamic behavior. The hybrid method uses the advantages of static and dynamic analysis and impact rather than it will improve the classification results. Therefore, expecting this approach is able to detect time and accuracy taken for each method to detect malware detection attack which lead to results.

Text FSKTM 2019 25 IR.pdf Download (1MB)

Actions (login required)

View Item