一种基于词向量的恶意代码分类模型

A word-vector based malware classification model

为提高大规模恶意代码分类任务的分类准确率,提出基于词向量的恶意代码分类模型,引入NLP中表达语义含义的词向量概念,提取恶意代码函数语义特征,使用textCNN神经网络对其进行分类。实验结果表明,该模型在微软公司提供的BIG2015恶意代码分类比赛的训练集上能实现98.78%的预测准确率,相较几种传统方法准确率分别提高0.91%~3.16%。

In order to improve the classification accuracy of large-scale malware classification tasks,a word-vector based malware classification model is proposed.The word vector concept which expressing semantic meaning in NLP is introduced to extract the semantic features of malware functions,and textCNN neural network is used for classification.The experimental results show that the model can achieve 98.78%prediction accuracy on the training set of BIG2015 malware classification challenge provided by Microsoft Corporation,which is 0.91%~3.16%higher than the accuracy of several traditional methods.