关键词: 恶意代码检测, 机器学习, 信息安全, 机器指令, 概率分布

Abstract: Nowadays, there are more and more various malicious code which cause a huge threat to the computer. In this paper, a variety of assembly instructions are well classified into three categories. And a novel algorithm is presented. In consideration of the relationship between instructions, this paper turn this relationship into probability distributions as the signature of the program. Then, using a large amount of samples to train. The experiment shows that the method proposed in this paper has a significant effect and high accuracy on detecting unknown and metamorphic programs.

Key words: malware detection, machine learning, information security, assembly instruction, probability distribution