Dr. Kamalakanta Sethi
A Novel Machine Learning Based Malware Detection and Classification Framework
6/1/2019
International Conference on Cyber Security and Protection of Digital Services (Cyber Security)
IEEE Explore
Abstract

As time progresses, new and complex malware types are being generated which causes a serious threat to computer systems. Due this drastic increase in the number of samples, signature-based detection techniques cannot provide accurate results. Different studies have demonstrated proficiency machine learning for classification files. Further, accuracy these models can be improved by using feature selection algorithms select most essential features reducing size dataset leads lesser computations. In paper, we developed based analysis framework efficient classification. We used Cuckoo sandbox dynamic executes an isolated environment generates report on system activities during execution. propose extraction module extracts from selects important ensuring high at minimum computation cost. Then, employ different fine-grained Experimental results show that got comparison state-of-the-art approaches.

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