2023 № 2 Сучасні інформаційні системи
Постійне посилання колекціїhttps://repository.kpi.kharkov.ua/handle/KhPI-Press/66396
Переглянути
Документ Biometric authentication utilizing convolutional neural networks(Національний технічний університет "Харківський політехнічний інститут", 2023) Datsenko, Serhii; Kuchuk, HeorhiiCryptographic algorithms and protocols are important tools in modern cybersecurity. They are used in various applications, from simple software for encrypting computer information to complex information and telecommunications systems that implement various electronic trust services. Developing complete biometric cryptographic systems will allow using personal biometric data as a unique secret parameter instead of needing to remember cryptographic keys or using additional authentication devices. The object of research the process of generating cryptographic keys from biometric images of a person's face with the implementation of fuzzy extractors. The subject of the research is the means and methods of building a neural network using modern technologies. The purpose of this paper to study new methods for generating cryptographic keys from biometric images using convolutional neural networks and histogram of oriented gradients. Research results. The proposed technology allows for the implementation of a new cryptographic mechanism - a technology for generating reliable cryptographic passwords from biometric images for further use as attributes for access to secure systems, as well as a source of keys for existing cryptographic algorithms.Публікація Generating currency exchange rate data based on Quant-GAN model(Національний технічний університет "Харківський політехнічний інститут", 2023) Bao, Dun; Zakovorotnyi, Oleksandr; Kuchuk, N. G.This paper discusses the use of machine learning algorithms to generate data that meets the demands of academia and industry in the context of exchange rate fluctuations. Research results. The paper builds a Quant-GAN model using temporal convolutional neural networks (CNN) and trains it on end-of-day and intraday high-frequency rates of currency pairs in the global market. The generated data is evaluated using various statistical methods and is found to effectively simulate the real dataset. Experimental results show that data generated by the model effectively fits statistical characteristics and typical facts of real training datasets with good overall fit. The results provide effective means for global FX market participants to carry out various tasks such as stress tests and scenario simulations. Future work includes accumulating data and increasing computing power, optimizing and improving GAN models, and establishing evaluation standards for generating exchange rate price data. As computing power continues to grow, the GAN model’s ability to process ultra-large-scale datasets is expected to improve.