Перегляд за Автор "Kuchuk, Nina"
Зараз показуємо 1 - 2 з 2
Результатів на сторінці
Налаштування сортування
Документ Designing and evaluating DL-model for vulnerability detection in smart contracts(Національний технічний університет "Харківський політехнічний інститут", 2023) Shmatko, Oleksandr; Kolomiitsev, Oleksii; Rekova, Nataliia; Kuchuk, Nina; Matvieiev, OleksandrTask features. Smart-contracts are programs that are stored in a distributed registry and execute code written in them in response to transactions addressed to them. Such smart- contracts are written in the Solidity programming language, which has a specific structure and syntax. The language was developed for the Ethereum platform. Having a specific structure, such languages are prone to certain vulnerabilities, the use of which can lead to large financial losses. Task statement. In this paper, a Deep Learning (DL) model is used to detect the vulnerabilities. Using the chosen approach and a properly specified input data structure, it is possible to detect complex dependencies between various program variables that contain vulnerabilities and bugs. Research results. Using well-defined experiments, this approach was investigated to better understand the model and improve its performance. The developed model classified vulnerabilities at the string level, using the Solidity corpus of smart-contracts as input data. The application of the DL model allows vulnerabilities of varying complexity to be identified in smart-contracts. Conclusions. Thus, the pipeline developed by us can capture more internal code information than other models. Information from software tokens, although semantically incapable of capturing vulnerabilities, increases the accuracy of models. The interpretability of the model has been added through the use of the attention mechanism. Operator accounting has shown significant performance improvements.Документ Practical principles of integrating artificial intelligence into the technology of regional security predicting(Національний технічний університет "Харківський політехнічний інститут", 2024) Shefer, Oleksandr; Laktionov, Oleksandr; Pents, Volodymyr; Hlushko, Alina; Kuchuk, NinaObjective. The aim is to enhance the efficiency of diagnostics for determining the level of air attack safety through the practical integration principles of artificial intelligence. Methodology. Models and technologies for safety diagnostics of the region (territorial community) have been explored. The process of building an artificial intelligence model requires differentiation of objects at a level to accumulate assessments-characteristics of aerial vehicles. The practical integration principles of artificial intelligence into the forecasting technology are based on the Region Safety Index, used for constructing machine learning models. The optimal machine learning model of the proposed approach is selected from a list of several models. Results. A technology for predicting the level of regional safety based on the Safety Index has been developed. The recommended optimal model is the Random Forest model ([('max_depth', 13), ('max_features', 'sqrt'), ('min_samples_leaf', 1), ('min_samples_split', 2), ('n_estimators', 79)]), demonstrating the most effective quality indicators of MAE; MAX; RMSE 0.005; 0.083; 0.0139, respectively. Scientific Novelty. The proposed approach is based on a linear model of the Region Safety Index, which, unlike existing ones, takes into account the interaction of factors. This allows for advantages of the proposed method over existing approaches in terms of the root mean square error of 0.496; 0.625, respectively. In turn, this influences the quality of machine learning models. Practical Significance. The proposed solutions are valuable for diagnosing the level of safety in the region of Ukraine, particularly in the context of air attacks.