A Computer Virus Detection Method Based on Information from PE Structure of Files Combined with Deep Learning Models

Autor:	Nguyen Hoang Anh, Pham Thi Vuong, Le Dinh Tuan, Mai Viet Tiep, Vu Thanh Nguyen, Vu Thanh Hien
Rok vydání:	2020
Předmět:	Structure (mathematical logic) business.industry Computer science Programming language Opcode Deep learning computer.file_format computer.software_genre Virus detection Computer virus Deep belief network Code (cryptography) Artificial intelligence business computer Portable Executable
Zdroj:	Future Data and Security Engineering. Big Data, Security and Privacy, Smart City and Industry 4.0 Applications ISBN: 9789813343696 FDSE (CCIS Volume)
Popis:	In this paper, we demonstrate a new approach to virus detection. Extract information from a file’s Portable Executable (PE) structure to save storage costs compared to other types of features such as signatures, opcodes, or file strings, while still detect unknown malicious code. Use a deep learning network, namely the Deep Belief Network (DBN) model to classify and train data. The results show that the accuracy of the method is quite high, can reach over 97% for ten properties and over 95% for 15 properties, respectively.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::abec0c1598578ae37911b01d1b67faeb https://doi.org/10.1007/978-981-33-4370-2_9 Zobrazit plný text záznamu