Grouping the Executables to Detect Malwares with High Accuracy

详细信息    查看全文

• 作者：Sanjay K. Sahay^a ; Ashu Sharma^b ; ^{p2012011@goa.bits-pilani.ac.in" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Anti-Malware ; Static Malware Analysis ; WEKA ; Machine Learning
• 刊名：Procedia Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：78
• 期：Complete
• 页码：667-674
• 全文大小：232 K

文摘

The metamorphic malware variants with the same malicious behavior (family), can obfuscate themselves to look different from each other. This variation in structure lead to a huge signature database for traditional signature matching techniques to detect them. In order to effective and effcient detection of malwares in large amounts of executables, we need to partition these files into groups which can identify their respective families. In addition, the grouping criteria should be chosen such a way that, it can also be applied to unknown files encounter on computer for classification. This paper discusses the study of malwares and benign executables in groups to detect unknown malwares with high accuracy. We studied sizes of malwares generated by three popular second generation malwares (metamorphic malwares) creator kits viz. G2, PS-MPC and NGVCK, and observed that the size variation in any two generated malwares from same kit is not much. Hence we grouped the executables on the basis of malware sizes by using Optimal k-Means Clustering algorithm and used these obtained groups to select promising features for training (Random forest, J48, LMT, FT and NBT) classifiers to detect variants of malwares or unknown malwares. We find that detection of malwares on the basis of their respected file sizes gives accuracy up to 99.11% from the classifiers.