A novel malware analysis for malware detection and classification using machine learning algorithms
10/13/2017
Proceedings of the 10th International Conference on Security of Information and Networks
ACM Digital Library
Abstract

Nowadays, Malware has become a serious threat to the digitization of world due emergence various new and complex malware every day. Due this, traditional signature-based methods for detection effectively becomes an obsolete method. The efficiency machine learning model in context files been proved by different researches studies. In this paper, framework developed detect classify (e.g exe, pdf, php, etc.) as benign malicious using two level classifier namely, Macro (for malware) Micro classification Trojan, Spyware, Adware, etc.). Cuckoo Sandbox is used generating static dynamic analysis report executing virtual environment. addition, novel extracting features based on static, behavioral network generated Sandbox. Weka Framework develop models training datasets.

Keywords
Advanced Malware Detection TechniquesNetwork Security and Intrusion DetectionAnomaly Detection Techniques and ApplicationsSignal ProcessingComputer Networks and CommunicationsArtificial Intelligence
Co-authors