%0 Conference Proceedings
%T A Deep Learning Approach for Network Anomaly Detection Based on AMF-LSTM
%+ Shenzhen Institutes of Advanced Technology (SIAT)
%A Zhu, Mingyi
%A Ye, Kejiang
%A Wang, Yang
%A Xu, Cheng-Zhong
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 15th IFIP International Conference on Network and Parallel Computing (NPC)
%C Muroran, Japan
%Y Feng Zhang
%Y Jidong Zhai
%Y Marc Snir
%Y Hai Jin
%Y Hironori Kasahara
%Y Mateo Valero
%I Springer International Publishing
%3 Network and Parallel Computing
%V LNCS-11276
%P 137-141
%8 2018-11-29
%D 2018
%R 10.1007/978-3-030-05677-3_13
%Z Computer Science [cs]Conference papers
%X The Internet and computer networks are currently suffering from different security threats. This paper presents a new method called AMF-LSTM for abnormal traffic detection by using deep learning model. We use the statistical features of multi-flows rather than a single flow or the features extracted from log as the input to obtain temporal correlation between flows, and add an attention mechanism to the original LSTM to help the model learn which traffic flow has more contributions to the final results. Experiments show AMF-LSTM method has high accuracy and recall in anomaly type identification.
%G English
%Z TC 10
%Z WG 10.3
%2 https://inria.hal.science/hal-02279546/document
%2 https://inria.hal.science/hal-02279546/file/477597_1_En_13_Chapter.pdf
%L hal-02279546
%U https://inria.hal.science/hal-02279546
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-TC
%~ IFIP-TC10
%~ IFIP-NPC
%~ IFIP-WG10-3
%~ IFIP-LNCS-11276