JavaScript malicious code detection method based on prototype dependency graph

• Main Authors: XIN YANG, YAO LIANGWEI, CHEN XINYI
• Format: Patent
• Language: Chinese; English
• Published: 14.05.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

According to the JavaScript malicious code detection method based on the prototype dependency graph, basic JavaScript malicious code detection is achieved, and meanwhile an improvement scheme is provided for the problem that the detection efficiency is low due to the fact that a traditional static detection method lacks semantic information. A prototype dependency graph is used for representing codes, and nodes in the graph and graph structure information are extracted through a graph neural network. The implementation process mainly comprises the steps of collecting and dividing data, constructing a prototype dependency graph, converting graph data, and training and predicting a graph neural network. The method specifically comprises the steps of crawling a data set, adding prototype information into a code representation method to form a prototype dependency graph, then pruning by using a graph pruning algorithm, encoding node types and edge types in the graph by using a FastText model, converting a text in