The Need for Speed: An Analysis of Brazilian Malware Classifiers

被引：26

作者：

Ceschin, Fabricio ^{[1
]}

Pinage, Felipe ^{[1
]}

Castilho, Marcos ^{[1
]}

Menotti, David ^{[1
]}

Oliveira, Luiz S. ^{[1
]}

Gregio, Andre ^{[1
]}

机构：

[1] Univ Fed Parana, Curitiba, Parana, Brazil

来源：

IEEE SECURITY & PRIVACY | 2018年 / 16卷 / 06期

关键词：

Malware;

D O I：

10.1109/MSEC.2018.2875369

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Using a dataset containing about 50,000 samples from Brazilian cyberspace, we show that relying solely on conventional machine-learning systems without taking into account the change of the subject's concept decreases the performance of classification, emphasizing the need to update the decision model immediately after concept drift occurs.

引用

页码：31 / 41

页数：11

共 15 条

[1] [Anonymous], 2014, ZDNet
[2] Baena-Garcia M., 2006, P 4 INT WORKSH KNOWL, P1
[3] The other guys: automated analysis of marginalized malware
Botacin, Marcus Felipe
de Geus, Paulo Licio
Abed Gregio, Andre Ricardo
[J]. JOURNAL OF COMPUTER VIROLOGY AND HACKING TECHNIQUES, 2018, 14 (01): : 87 - 98
[4] Damien A., 2016, TFLEARN DEEP LEARNIN
[5] David O.E., 2015, 2015 INT JOINT C NEU, P1, DOI DOI 10.1109/IJCNN.2015.7280815
[6] Gama J, 2004, LECT NOTES ARTIF INT, V3171, P286
[7] Gregio A.R. A., 2013, Proceedings of the 28th Annual ACM Symposium on Applied Computing, P1830
[8] Pedregosa F, 2011, J MACH LEARN RES, V12, P2825
[9] Pietrek M., 2016, PEERING INSIDE PE TO
[10] Classification systems in dynamic environments: an overview
Pinage, Felipe Azevedo
dos Santos, Eulanda Miranda
Portela da Gama, Joao Manuel
[J]. WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY, 2016, 6 (05) : 156 - 166

← 1 2 →