A Deep Learning Approach for Network Anomaly Detection Based on AMF-LSTM
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.
This work is supported by the National Key R&D Program of China (No. 2018YFB1004804), National Natural Science Foundation of China (No. 61702492, U1401258), and Shenzhen Basic Research Program (No. JCYJ20170818153016513, JCYJ20170307164747920).
- 3.Benson, T., Akella, A., Maltz, D.A.: Network traffic characteristics of data centers in the wild. In: Proceedings of the 10th ACM SIGCOMM Conference on Internet Measurement, pp. 267–280 (2010)Google Scholar
- 6.Chorowski, J.K., Bahdanau, D., Serdyuk, D., Cho, K., Bengio, Y.: Attention-based models for speech recognition. In: Advances in Neural Information Processing Systems, pp. 577–585 (2015)Google Scholar
- 8.Intrusion detection evaluation dataset (cicids2017) (2018). http://www.unb.ca/cic/datasets/ids-2017.html
- 9.Mcafee labs threats report (2018). https://www.mcafee.com/cn/security-awareness/articles/mcafee-labs-threats-report-mar-2016.aspx
- 13.Khan, M.S.A.: Rule based network intrusion detection using genetic algorithm. Int. J. Comput. Appl. 18(8), 26–29 (2011)Google Scholar
- 15.Thilina, A., et al.: Intruder detection using deep learning and association rule mining. In: IEEE International Conference on Computer and Information Technology (CIT), pp. 615–620 (2016)Google Scholar
- 17.Kim, J., Kim, J., Thu, H.L.T., Kim, H.: Long short term memory recurrent neural network classifier for intrusion detection. In: International Conference on Platform Technology and Service (PlatCon), pp. 1–5 (2016)Google Scholar