CREATING PROGRAM CLASSIFYING REQUESTS
Keywords:
neural networks, under-sampling, IPSAbstract
In this article is described prototype of application which solves problem of classification requests as secure and dangerous. Neural networks are demonstrated as tool for automation of request processing. Implementation of algorithm is going to be taken from tensorflow and NSL-KDD library as source of training data for neural network.
References
Matthew K. Thoughtful Machine Learning with python. A test-driven approach. – O`Reilly 2017. – 216 с.
Clarence Chio, David Freeman Machine Learning and Security Protecting Systems with data and algorithms. – O`Reilly 2018. – 385
Security Architecture Vulnerabilities URL: https://resources.infosecinstitute.com/category/certifications-training/cissp/domains/security-engineering/security-architecture-vulnerabilities (request date 11.05.2020).
Rowland, Craig H. "Intrusion detection system." U.S. Patent No. 6,405,318. 11 Jun. 2002.
Classify structured data URL: https://www.tensorflow.org/tutorials/structured_data/feature_columns?hl=ru (request date 11.05.2020).
Description of library generating new items URL: https://imbalanced-learn.readthedocs.io/en/stable/generated/imblearn.over_sampling.SMOTE.html (request date 7.05.2020)
Files as source to neural network URL: https://web.archive.org/web/20150205070216/http://nsl.cs.unb.ca/NSL-KDD (request date 6.04.2020)
Examples of IPSs URL: https://www.comparitech.com/net-admin/ips-tools-software/(request 11.05.2020)