Resumo de Grandes Volumes de Dados com Filtro de Bloom: Uma Abordagem Eficiente para Aprendizado Profundo com Redes Neurais Convolucionais em Fluxos de Rede

• Martin Andreoni Lopez TII
• Diogo M. F. Mattos UFF

DOI: https://doi.org/10.5753/sbrc.2021.16745

Abstract

This paper proposes using Bloom filters to generate summaries of two-dimensional data from flows in a network usage window, forming a bitmap. After generating the summaries, the paper applies deep learning, composed of layers of a convolutional neural network to segment the bitmap. Bitmap segmentation is a computer vision task that convolutional neural networks efficiently provide. The main contributions of the paper are three-fold: (i) the proposal of a two-dimensional data summary technique in a flow window through Bloom filters; (ii) the deployment of deep learning with convolutional neural networks over network flows; and (iii) the optimized execution of our proposal in graphic processing units (GPU). We evaluate the proposal on a real dataset from a broadband access provider, and the results demonstrate the efficiency of the filters and the high precision on the incremental deep learning deployment.

References

Andreoni Lopez, M., Mattos, D. M. F., Duarte, O. C. M. B. e Pujolle, G. (2019). Toward a monitoring and threat detection system based on stream processing as a virtual network function for big data. Concurrency and Computation: Practice and Experience, 31(20):1–17.

Andreoni Lopez, M., Sanz, I. J., Lobato, A. G. P., Mattos, D. M. F. e Duarte, O. C. M. B. (2018). Aprendizado de máquina em plataformas de processamento distribuído de uxo: Análise e detecção de ameaças em tempo real. Minicursos do Simpósio Brasileiro de Redes de Computadores-SBRC, 2018:150–206.

Andreoni Lopez, M., Silva, S. R., Alvarenga, I. D., Rebello, G. A. F., Sanz, J. I., Lobato, A. G. P., Mattos, D. M. F., Duarte, O. C. M. B. e Pujolle, G. (2017). Collecting and Characterizing a Real Broadband Access Network Traffic Dataset. Em IEEE/IFIP 1st Cyber Security in Networking Conference (CSNet’17), p. 1–8, Brazil.

Casas, P., Soro, F., Vanerio, J., Settanni, G. e D’Alconzo, A. (2017). Network security and anomaly detection with big-dama, a big data analytics framework. Em 2017 IEEE 6th International Conference on Cloud Networking (CloudNet), p. 1–7.

de Oliveira, M. T., Reis, L. H. A., Medeiros, D. S. V., Carrano, R. C., Olabarriaga, S. D. e Mattos, D. M. F. (2020). Blockchain reputation-based consensus: A scalable and resilient mechanism for distributed mistrusting applications. Comput. Networks, 179:107367.

de Oliveira, N. R., Pisa, P. S., Lopez, M. A., de Medeiros, D. S. V. e Mattos, D. M. F. (2021). Identifying fake news on social networks based on natural language processing: Trends and challenges. Information, 12(1).

de Souza, L. A. C., Antonio F. Rebello, G., Camilo, G. F., Guimarães, L. C. B. e Duarte, O. C. M. B. (2020). Dfedforest: Decentralized federated forest. Em 2020 IEEE International Conference on Blockchain (Blockchain), p. 90–97.

Doriguzzi-Corin, R., Millar, S., Scott-Hayward, S., Martínez-del-Rincón, J. e Siracusa, D. (2020). Lucid: A practical, lightweight deep learning solution for ddos attack detection. IEEE Transactions on Network and Service Management, 17(2):876–889.

Hwang, R.-H., Peng, M.-C., Huang, C.-W., Lin, P.-C. e Nguyen, V.-L. (2020). An unIEEE supervised deep learning model for early network traffic anomaly detection. Access, 8:30387–30399.

Jo, W., Kim, S., Lee, C. e Shon, T. (2020). Packet preprocessing in cnn-based network intrusion detection system. Electronics, 9(7):1151.

Kato, N., Fadlullah, Z. M., Mao, B., Tang, F., Akashi, O., Inoue, T. e Mizutani, K. (2017). The deep learning vision for heterogeneous network traffic control: Proposal, challenges, and future perspective. IEEE Wireless Communications, PP(99):2–9.

Kwon, D., Natarajan, K., Suh, S. C., Kim, H. e Kim, J. (2018). An empirical study on network anomaly detection using convolutional neural networks. Em 2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS), p. 1595–1598. IEEE.

Laufer, R. P., Velloso, P. B. e Duarte, O. C. M. B. (2011). A generalized bloom filter to secure distributed network applications. Computer Networks, 55(8):1804–1819.

Liu, W., Wang, Z., Liu, X., Zeng, N., Liu, Y. e Alsaadi, F. E. (2017). A survey of deep neural network architectures and their applications. Neurocomputing, 234:11–26.

Lobato, A. G. P., Andreoni Lopez, M., Sanz, I. J., Cardenas, A. A., Duarte, O. C. M. B. e Pujolle, G. (2018). An adaptive real-time architecture for zero-day threat detection. Em 2018 IEEE International Conference on Communications (ICC), p. 1–6.

Qin, Y., Shen, G.-w., Zhao, W.-b., Chen, Y.-p., Yu, M. e Jin, X. (2019). A network security entity recognition method based on feature template and cnn-bilstm-crf. Frontiers of Information Technology & Electronic Engineering, 20(6):872–884.

Reis, L. H. A., Murillo Piedrahita, A., Rueda, S., Fernandes, N. C., Medeiros, D. S. V., de Amorim, M. D. e Mattos, D. M. F. (2020). Unsupervised and incremental learning orchestration for cyber-physical security. Transactions on Emerging Telecommunications Technologies, 31(7):e4011.

Silva, J. V. V., Andreoni Lopez, M. e Mattos, D. M. F. (2020). Attackers are not stealthy: Statistical analysis of the well-known and infamous kdd network security dataset. Em 2020 4th Conference on Cloud and Internet of Things (CIoT), p. 1–8.

Sultana, F., Sufian, A. e Dutta, P. (2020). Evolution of image segmentation using deep convolutional neural network: A survey. Knowledge-Based Systems, 201-202:106062.

Viegas, E., Santin, A., Bessani, A. e Neves, N. (2019). Bigow: Real-time and reliable anomaly-based intrusion detection for high-speed networks. Future Generation Computer Systems, 93:473 – 485.

Wang, Z. e Majewicz Fey, A. (2018). Deep learning with convolutional neural network for objective skill evaluation in robot-assisted surgery. International Journal of Computer Assisted Radiology and Surgery, 13(12):1959–1970.

Xiao, P., Li, Z., Qi, H., Qu, W. e Yu, H. (2016). An efficient ddos detection with bloom filter in sdn. Em 2016 IEEE Trustcom/BigDataSE/ISPA, p. 1–6. IEEE.

Zhang, Y., Chen, X., Guo, D., Song, M., Teng, Y. e Wang, X. (2019). Pccn: Parallel cross convolutional neural network for abnormal network traffic ows detection in multiclass imbalanced network traffic ows. IEEE Access, 7:119904–119916.