DETECTION OF MALWARE USING DEEP LEARNING AND MACHINE LEARNING ALGORITHMS

---

H. Shanthi
Assistant Professor, Department of Electronics and Communication Engineering, Sridevi Women’s Engineering College, Hyderabad, India, ttshanthi876@gmail.com

M. Kalpana
U.G Student, Department of Electronics and Communication Engineering, Sridevi Women’s Engineering College, Hyderabad, India

M. Pavani
U.G Student, Department of Electronics and Communication Engineering, Sridevi Women’s Engineering College, Hyderabad, India

P. Nandini
U.G Student, Department of Electronics and Communication Engineering, Sridevi Women’s Engineering College, Hyderabad, India

Vol 17, No 07 ( 2022 )   |  DOI: 10.5281/zenodo.6877502   |   Licensing: CC 4.0   |   Pg no: 139-149   |   Published on: 25-07-2022

---

Abstract
Malware has become a significant downside in computers resulting in a rise in malware attacks within the kind of malicious software system. Previous malware sleuthing techniques were supported Static and Dynamic analysis of malware. As these techniques are long recent malware use Machine Learning algorithms like Deep learning algorithms and polymorphic, metamorphic techniques to enhance malware detection. There's a requirement to mitigate bias and measure these strategies severally to make new increased strategies for effective zero-day malware detection. During this paper, we have a tendency to find and measure the malware mistreatment Machine Learning algorithms (MLAs) and deep learning architectures for detection, classification, and categorization of malware by providing datasets and validators all the machine learning and deep learning algorithms. Then we are going to determine the accuracy, precision, and prediction of each formula then compare them and find that malware is gift within the given dataset. Overall, this work proposes an efficient visual detection of malware employing an ascendable and hybrid deep learning framework for period of time deployments. Therefore, the deep learning and machine learning algorithms for static, dynamic, and image process analysis approach could be a new technique for malware detection. A proof-of-concept model has been developed for example the effectiveness of the projected system.

Keywords:
Malware detection, Static and Dynamic Analysis, Machine Learning, Deep Learning, Image Processing

---

Download Full Article PDF