USE OF MACHINE LEARNING IN CYBER SECURITY
DOI:
https://doi.org/10.28925/2663-4023.2021.12.132142Keywords:
machine learning, cybersecurity, neural networks, cyberattack, cybersecurity using machine learningAbstract
The urgency of the topic is the integration of machine learning technologies into cybersecurity systems. After getting acquainted with the technical literature, the main technologies of machine learning that are implemented in the organization of cybersecurity were formulated. Acquainted with the main type of artificial neural network used in the prevention and detection of cyber threats and found that the main to consider the general application of machine learning technologies are artificial neural networks based on a multilayer perceptron with inverse error propagation. It is proposed to use indicators of compromise cyberattacks as initial information for automatic machine learning systems. Emphasis is placed on the main types of data that can be used by surveillance subsystems for information security and cybersecurity to perform tasks and prevent, classify and predict cybersecurity events. According to the results of the analysis, the main problem areas for their implementation in information security systems are identified. The problem of using machine learning (ML) in cybersecurity is difficult to solve, because advances in this area open up many opportunities, from which it is difficult to choose effective means of implementation and decision-making. In addition, this technology can also be used by hackers to create a cyber attack. The purpose of the study is to implement machine learning in information security and cybersecurity technology, and to depict a model based on self-learning
Downloads
References
Ciaramella, P. DArco, A. De Santis, C. Galdi, R. Tagliaferri. (2006). Neural Network Techniques for Proactive Password Checking. IEEE Transactions on Dependable and Secure Computing, 3(4), 327-339.
Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, A. Courville. (2017). Improved training of wasserstein GANs. In Proc. of the 31st International Conference on Neural Information Processing Systems, (pp. 5769-5779).
Shodan search engine. (b. d.). Shodan Search Engine. https://www.shodan.io/
Skrыpnykov, A. V., Denysenko, V.V., Saranov, Y.A. (2020). Yspolzovanye metodov mashynnoho obuchenyia pry reshenyy zadach ynformatsyonnoi bezopasnosty. Voronezhskyi hosudarstvennыi unyversytet ynzhenernыkh tekhnolohyi, 4, 69–79.
Le Roux, N., Bengio, Y. (2008). Representational power of restricted Boltzmann machines and deep belief networks. Neural computation, 20(6), 1631-1649.
Sharma, B., Mangrulkar, R. (2019). Deep learning applications in cyber security: a comprehensive review, challenges and prospects. International Journal of Engineering Applied Sciences and Technology, 4(8), 148-159
Ranzato, M.A., Boureau, Y.L., Cun, Y.L. (2008). Sparse feature learning for deep belief networks. Advances in neural information processing systems, (pp. 1185-1192).
Mirkin, B. G. (2011). Core concepts in data analysis: Summarization, correlation and visualization. Springer Science & Business Media.
https://www.theverge.com/2018/1/12/16882408/google-racist-gorillas-photo-recognition-algorithm-ai
https://www.kaspersky.com/enterprise-security/wiki-section/products/sandbox
Kazennov, A. M. (2010). Basic concepts of CUDA technology. Computer Research and Modeling, 2(3), 295–308. https://doi.org/10.20537/2076-7633-2010-2-3-295-308
Loskutov, A. (Red.). (2003). Neirosetevыe alhorytmы prohnozyrovanyia y optymyzatsyy system. Nauka y Tekhnyka.
