RT info:eu-repo/semantics/conferenceProceedings
T1 A review of: Optimal feature configuration for dynamic malware detection
A1 Escudero García, David
A1 Castro García, Noemí de
A2 FuentesJosé María de
A2 GonzálezLorena
A2 SanchoJosé Carlos
A2 AyerbeAna
A2 EscalanteMaría Luisa
A2 Matematica Aplicada
K1 Ingeniería de sistemas
K1 Machine learning
K1 Malware detection
K1 Feature engineering
K1 1203.17 Informática
K1 1207.02 Sistemas de Control
AB [EN] Applying machine learning techniques to malware detection is a common approach to try to overcome the limitations of signature-based methods. However, it is difficult to engineer a set of features that characterizes the samples properly, especially when various file types may be a vector of infection. In this work, we configure several feature sets for dynamic malware detection extracted from API calls, network activity, signaturesfrom the Cuckoo sandbox report, and some interactions with the file system and registry. We test combinations of these feature sets to ascertain whether they are good enough to distinguish between benign and malicious samples from a dataset containing several file types, obtained from public sources. The datasets present class imbalance to evaluate the model performance on more realistic scenarios in which not many malware samples are available
PB Fundación Tecnalia Research and Innovation
SN 978-84-88734-13-6
LK https://hdl.handle.net/10612/20307
UL https://hdl.handle.net/10612/20307
NO Escudero García, D., & DeCastro García, N. (2022). A review of: Optimal Feature Configuration forDynamic Malware Detection. En J. M. de Fuentes, L. González Manzano, J. C. Sancho Núñez, A. Ayerbe, & L. M. Alcocer Escalante (eds.), Investigación en Ciberseguridad Actas de las VII Jornadas Nacionales (7º.2022.Bilbao) (pp. 277-278). Fundación Tecnalia Research and Innovation.
DS BULERIA. Repositorio Institucional de la Universidad de León
RD 02-jun-2024