Deep Learning Based Hybrid Analysis of Malware Detection and Classification: A Recent Review
Abstract: Globally extensive digital revolutions involved with every process related to human progress can easily create the critical issues in security aspects. This is promoted due to the important factors like financial crises and geographical connectivity in worse condition of the nations. By this fact, the authors are well motivated to present a precise literature on malware detection with deep learning approach. In this literature, the basic overview includes the nature of nature of malware detection i.e., static, dynamic, and hybrid approach. Another major component of this articles is the investigation of the backgrounds from recently published and highly cited state-of-the-arts on malware detection, prevention and prediction with deep learning frameworks. The technologies engaged in providing solutions are utilized from AI based frameworks like machine learning, deep learning, and hybrid frameworks. The main motivations to produce this article is to portrait clear pictures of the option challenging issues and corresponding solution for developing robust malware-free devices. In the lack of a robust malware-free devices, highly growing geographical and financial disputes at wide globes can be extensively provoked by malicious groups. Therefore, exceptionally high demand of the malware detection devices requires a very strong recommendation to ensure the security of a nation. In terms preventing and recovery, Zero-day threats can be handled by recent methodology used in deep learning. In the conclusion, we also explored and investigated the future patterns of malware and how deals with in upcoming years. Such review may extend towards the development of IoT based applications used many fields such as medical devices, home appliances, academic systems.
Deep Learning Based Hybrid Analysis of Malware Detection and Classification: A Recent Review
DOI: https://doi.org/10.13052/jcsm2245-1439.1314
Keywords: Malware detection, distributed denial of services, artificial intelligence, Deep Learning, static and dynamic analysis
Syed Shuja Hussain, Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah, Malaysia
Syed Shuja Hussain has received BS degree in Computer Engineering from the Sir Syed University of Engineering and Technology (SSUET), Pakistan and MS degree in Telecommunication Engineering from University of Engineering and Technology (UET) Peshawar, Pakistan. He is pursuing a Ph.D. from the Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA), Malaysia. He has been involved in research work on Android malware analysis.
Mohd Faizal Ab Razak, Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah, Malaysia
Mohd Faizal Ab Razak has distinctively received his PhD from University of Malaya and Master of Computer Science (Networking) from Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA), Malaysia. He is currently a lecturer and researcher at Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA), Malaysia. His area of research includes Mobile Computing, Intrusion Detection System, risk assessment, network security and Mobile Security.
Ahmad Firdaus, Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah, Malaysia
Ahmad Firdaus distinctively received his PhD from University of Malaya (UM), Malaysia. He also obtained his Master of Computer Science (Networking) from Universiti Teknologi Mara (UiTM), Malaysia. He is currently a senior lecturer at the Faculty of Computing at Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA), Malaysia. His area of research includes Mobile Security, Intrusion Detection System and Blockchain.
