ISBN: 978-981-11-3671-9 DOI: 10.18178/wcse.2017.06.241
A Virus Detection Model Based on Artificial immunity System
Abstract— Many new research of virus detection appeared with the development of machine learning and
artificial intelligence. The biggest drawback of traditional virus detection methods is that it’s powerless for
unknown viruses and new varieties detection. This situation is gradually improved owing to the introduction
of intelligent learning algorithm. Anyway, the existing virus detection methods still have some problems such
as low detection rate and poor ability of anti-obfuscation. In order to solve these problems, this paper
proposed a virus detection model based on artificial immune system and sub-graph pattern mining. First of
all, we extract the semantic features of malicious files by unpacking process, static analysis and call graph
construction. Then, convert it to DFS code Graph and carry on pattern sub-graph mining to get virus
candidate feature library. Finally, use the negative selection algorithm to deal with the virus candidate feature
library of malicious files and the feature database of benign files to get virus feature library. The
experimental results show that the model has a high ACC value for unknown viruses and new varieties, with
an average of over 97%.
Index Terms— Virus detection, Artificial immunity system, Negative selection, Semantic features, Sub-graph
pattern mining
Huakang Xing, Zhengping Jin
State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and
Telecommunications, CHINA
Zhengmin Li
National Computer Network Emergency Response Technical Team/Coordination Center of China, CHINA
Institute of Information Engineering, Chinese Academy of Sciences (IIE, CAS), CHINA
ISBN: 978-981-11-3671-9 DOI: 10.18178/wcse.2017.06.17Xsrc="http://www.wcse.org/uploadfile/2019/0823/20190823055609629.png" style="width: 120px; height: 68px;" />[Download]
Cite: Huakang Xing, Zhengmin Li, Zhengping Jin, "A Virus Detection Model Based on Artificial immunity System," Proceedings of 2017 the 7th International Workshop on Computer Science and Engineering, pp. 1392-1397, Beijing, 25-27 June, 2017.