Efficient Malicious Code Detection Using N-Gram Analysis and SVM

As the use of the internet increases, the distribution of web based malicious code has also vastly increased. By inputting malicious code that can attack vulnerabilities, it enables one to perform various illegal acts, such as SQL Injection and Cross Site Scripting (XSS). Furthermore, an extensive amount of computer, network and human resources are consumed to prevent it. As a result much research is being done to prevent and detecting malicious code. Currently, research is being done on readable sentences which do not use proper grammar. This type of malicious code cannot be classified by previous vocabulary analysis or document classification methods. This paper proposes an approach that results in an effective n-gram feature extraction from malicious code for classifying executable as malicious or benign with the use of Support Vector Machines (SVM) as the machine learning classifier.