PDF Publication Title:
Text from PDF Page: 181
particular samples associated with the labels. This association is usually noisy and identifying a canonical set of samples associated with each label can be complex. Therefore, the proposed model streamlines the data generation process based on the intrusion label. We have analyzed different VAE architecture variants for the proposed model, providing an extensive study on the alternatives. When considering all experiments carried out to determine the similarity of synthetic data to real intrusion detection data, and its capacity to be used as new training data we can conclude that the model based on conditional VAE with Gaussian and Bernoulli distributions presents the best results. Also, we provide a comparison of our best model with seven common SOTA over-sampling algorithms (SMOTE, ADASYN...), showing that the synthetic data generated by our proposed model offer better metrics of average performance (accuracy, F1) when four common classifiers are trained with this data, compared to the results obtained with the data generated by the alternative algorithms. This indicates that the data generated with the proposed model is closer to the original data and can better reproduce the probability distribution of its features. Acknowledgments This work has been partially funded by the Ministerio de Economía y Competitividad del Gobierno de España and the Fondo de Desarrollo Regional (FEDER) within the project "Inteligencia distribuida para el control y adaptación de redes dinámicas definidas por software, Ref: TIN2014-57991-C3-2-P", in the Programa Estatal de Fomento de la Investigación Científica y Técnica de Excelencia, Subprograma Estatal de Generación de Conocimiento. References [1] Kingma DP, Welling M (2014) Auto-Encoding Variational Bayes. arXiv:1312.6114v10 [stat.ML] [2] Goodfellow IJ, Pouget-Abadie J, Mirza M et al (2014) Generative Adversarial Networks. arXiv:1406.2661v1 [stat.ML] [3] Miao Y, Yu L, Blunsom P (2015) Neural Variational Inference for Text Processing. arXiv:1511.06038 [cs.CL]. [4] Yang Z, Hu Z, Salakhutdinov R et al (2017) Improved Variational Autoencoders for Text Modeling using Dilated Convolutions. arXiv:1702.08139 [cs.NE]. [5] Goodfellow IJ, Shlens J, Szegedy C (2015) Explaining and Harnessing Adversarial Examples. arXiv:1412.6572 [stat.ML]. [6] Galar M, Fernandez A, Barrenechea E et al (2012) A Review on Ensembles for the Class Imbalance Problem: Bagging-, Boosting-, and Hybrid-Based Approaches. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 42, no. 4, pp. 463- 484 [7] He H, Garcia EA (2009) Learning from Imbalanced Data. IEEE Transactions on Knowledge and Data Engineering, vol. 21, no. 9, pp. 1263-1284. [8] Weiss G (2004) Mining with rarity: a unifying framework. ACM SIGKDD Explorations, vol. 6. no. 1. pp. 7-19. [9] Chawla NV, Bowyer KW, Hall LO et al (2002) SMOTE: synthetic minority over- sampling technique. Journal of artificial intelligence research, vol. 16. pp. 321-357. [10] Han H, Wen-Yuan W, Bing-Huan M, (2005) Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning. Advances in intelligent computing, pp. 878-887. Doctoral Thesis: Novel applications of Machine Learning to NTAP - 179PDF Image | Novel applications of Machine Learning to Network Traffic Analysis
PDF Search Title:
Novel applications of Machine Learning to Network Traffic AnalysisOriginal File Name Searched:
456453_1175348.pdfDIY PDF Search: Google It | Yahoo | Bing
Cruise Ship Reviews | Luxury Resort | Jet | Yacht | and Travel Tech More Info
Cruising Review Topics and Articles More Info
Software based on Filemaker for the travel industry More Info
The Burgenstock Resort: Reviews on CruisingReview website... More Info
Resort Reviews: World Class resorts... More Info
The Riffelalp Resort: Reviews on CruisingReview website... More Info
| CONTACT TEL: 608-238-6001 Email: greg@cruisingreview.com | RSS | AMP |