Malware Variant Identification Using Incremental Clustering
Open Access
- 8 July 2021
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 10 (14) , 1628
Abstract
Dynamic analysis and pattern matching techniques are widely used in industry, and they provide a straightforward method for the identification of malware samples. Yara is a pattern matching technique that can use sandbox memory dumps for the identification of malware families. However, pattern matching techniques fail silently due to minor code variations, leading to unidentified malware samples. This paper presents a two-layered Malware Variant Identification using Incremental Clustering (MVIIC) process and proposes clustering of unidentified malware samples to enable the identification of malware variants and new malware families. The novel incremental clustering algorithm is used in the identification of new malware variants from the unidentified malware samples. This research shows that clustering can provide a higher level of performance than Yara rules, and that clustering is resistant to small changes introduced by malware variants. This paper proposes a hybrid approach, using Yara scanning to eliminate known malware, followed by clustering, acting in concert, to allow the identification of new malware variants. score and V-Measure clustering metrics are used to evaluate our results.
Keywords
This publication has 22 references indexed in Scilit:
- Familial Clustering for Weakly-Labeled Android Malware Using Hybrid Representation LearningIEEE Transactions on Information Forensics and Security, 2019
- Performance Evaluation of Features and Clustering Algorithms for Malware2018
- Detecting Ransomware using Support Vector Machines2018
- How to detect the Cuckoo Sandbox and to Strengthen it?Journal of Computer Virology and Hacking Techniques, 2014
- Growing Grapes in Your Computer to Defend Against MalwareIEEE Transactions on Information Forensics and Security, 2013
- Automatic analysis of malware behavior using machine learningJournal of Computer Security, 2011
- Toward Automated Dynamic Malware Analysis Using CWSandboxIEEE Security & Privacy, 2007
- A new nonsmooth optimization algorithm for minimum sum-of-squares clustering problemsEuropean Journal of Operational Research, 2006
- Estimating the Number of Clusters in a Data Set Via the Gap StatisticJournal of the Royal Statistical Society Series B: Statistical Methodology, 2001
- BIRCH: A New Data Clustering Algorithm and Its ApplicationsData Mining and Knowledge Discovery, 1997