Malware Detection using Deep Learning Methods
Nourin N.S1, Sulphikar A2
1Nourin N.S*, Department of Computer Science and Engineering, LBSITW, Trivandrum, India.
2Sulphikar A, Department of Computer Science and Engineering, LBSITW, Trivandrum, India.
Manuscript received on April 01, 2020. | Revised Manuscript received on April 10, 2020. | Manuscript published on April 15, 2020. | PP: 6-9 | Volume-6, Issue-6, April 2020. | Retrieval Number: F1218046620/2019©BEIESP | DOI: 10.35940/ijisme.F1218.046620
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Rapid development of the internet leads the malware to become one of the most significant threads nowadays. Malware, is any kind of program or file which would adversely affect the computer users in a harmful way. Malware exist in different forms which includes worms, viruses in computer, Trojan horses, etc. These malicious contents can degrade the overall performance of the system. It includes activities like stealing, encrypting or deleting sensitive data, etc. without the consent of the user. Malware detection is a milestone in the field of computer security. For detecting malware many methods have been evolved. Researchers are mainly concentrated in malware identification methods based on machine learning. Malware can be detected in two ways. They are static approach and dynamic approach. This paper mainly deals with the current challenges faced by malware detection methods and also explores a categorized new method in machine learning. The methods discussed here are combined static and dynamic approach, random forest, Bayes classification. This work will help in cyber security area and also which will help the researchers to do efficient researches.
Keywords: Computer Security, Dynamic Analysis, Machine Learning, Malware Detection, Static Analysis.