Malware (Malicious Software) is a program that can harm the computers/mobiles/networks and affects their normal functioning. As the computational needs are diversified, security threats are also getting complex to be detected. The traditional approaches require updation and are not able to cover the entire definitions of each kind of malicious code patterns. Therefore, an improvement in traditional approach is required to be incorporated. In this work, it is intended to search an adaptive approach by which the machine can learn and update itself from the last learning. Two different appropriate data models namely C4.5 decision tree and Bayes classifier have been used in this paper. Both the data models are promising and provide accurate classification with some limitations. To make improvement on it, a hybrid classification approach is designed using C4.5 decision tree and Bayes classifier. This work is implemented in JAVA and performance is evaluated on several parameters such as classification accuracy, space and time complexity. As per the obtained results, it is evident that the proposed technique is more accurate and efficient as compared to the respective implemented algorithms.
CITATION STYLE
Kumar, A., Singh, S. S., Singh, K., Shakya, H. K., & Biswas, B. (2019). An Implementation of Malware Detection System Using Hybrid C4.5 Decision Tree Algorithm. In Communications in Computer and Information Science (Vol. 956, pp. 579–589). Springer Verlag. https://doi.org/10.1007/978-981-13-3143-5_48
Mendeley helps you to discover research relevant for your work.