Publication Type : Conference Paper
Publisher : 2020 International Conference on Inventive Computation Technologies (ICICT)
Source : 2020 International Conference on Inventive Computation Technologies (ICICT) (2020)
Url : https://ieeexplore.ieee.org/abstract/document/9112437
Keywords : automated anti-malware systems, classification, Classification process, digital age, digital environment, feature, Feature selection, invasive software, malware, Malware analysis, malware attacks, Malware Classification, Malware families, nonnetwork Malware classification, optimal feature selection, Pattern classification
Campus : Coimbatore
School : School of Engineering
Department : Computer Science
Year : 2020
Abstract : In this digital age, almost every system and service has moved from a localized to a digital environment. Consequently the number of attacks targeting both personal as well as commercial digital devices has also increased exponentially. In most cases specific malware attacks have caused widespread damage and emotional anguish. Though there are automated techniques to analyse and thwart such attacks, they are still far from perfect. This paper identifies optimal features, which improves the accuracy and efficiency of the classification process, required for malware classification in an attempt to assist automated anti-malware systems identify and block malware families in an attempt to secure the end user and reduce the damage caused by these malicious software.
Cite this Research Publication : K. S. ManiArasuSekar, Swaminathan, P., Ritwik Murali, Ratan, G. K., and Siva, S. V., “Optimal Feature Selection for Non-Network Malware Classification”, in 2020 International Conference on Inventive Computation Technologies (ICICT), 2020.