Affiliation:
1. ALTINBAS UNIVERSITY
2. YILDIZ TECHNICAL UNIVERSITY
Abstract
Background/aim: The aim of this study is to benefit from deep learning algorithms in the classification of malware. It is to determine the most effective classification algorithm by comparing the performances of deep learning algorithms.
Materials and methods: In this study, three deep learning methods, namely Long-Short-Term Memory Network (LSTM), Convolutional Neural Network (CNN), and Multitasking Deep Neural Network (DNN) were used.
Results: According to the findings obtained in malware detection, the best results were obtained from LTSM, CNN and DNN methods, respectively. With the three deep learning algorithms, the average Accuracy was 96%, the Precision average was 97%, and the Recall average was 97%.
Conclusion: According to the most effective results obtained from this study, Accuracy 0.982, Precision 0.988 and Recall 0.990.
Reference22 articles.
1. Alzaylaee, M. K., Yerima, S. Y., & Sezer, S. (2020). DL-Droid: Deep learning based android malware detection using real devices. Computers & Security, 89, 101663.
2. Aycock, J. (2006). Computer viruses and malware (Vol. 22). Springer Science & Business Media.
3. Cheng, Y., Fu, S., Tang, M., & Liu, D. (2019). Multi-task deep neural network (MT-DNN) enabled optical performance monitoring from directly detected PDM-QAM signals. Optics express, 27(13), 19062-19074.
4. Danniels, M. "Denial of Service Attacks," Imperva, 2015. [Online]. Available: https://www.incapsula.com/ddos/ddos-attacks/denial-of-service.html. [Accessed 17 Juny 2015]
5. He, K., & Kim, D. S. (2019, August). Malware detection with malware images using deep learning techniques. In 2019 18th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/13th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE) (pp. 95-102). IEEE.
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献