Based on the Semantics Analysis of the URL Identification and Malicious Code Detection

The traditional malicious URL identification methods usually adopt blacklist technology, heuristic algorithm and machine learning algorithm. This paper considers that natural language processing technology can be introduced when dealing with text with context. This technique is used to help computers understand, interpret, and manipulate human language. It is often used to deal with contextual problems, and when combined with malicious URL directions, it can produce more accurate models than existing methods. In addition to the traditional TF-IDF detection method, this paper introduces N-Gram and Word2vec methods for the first time, a total of three different natural language processing technologies to process and extract URL data. Through a series of experiments, this paper proves that semantic analysis can improve the accuracy of malicious code detection successfully by adjusting parameters of the optimization model. The final experimental results show that the detection rate of malicious URLs by TF-IDF method and N-Gram method combined with various machine learning models is about 85%, while the detection rate of Word2vec method combined with deep learning model reaches 99%, and the detection accuracy is significantly improved.