Diana A. Fedash
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Diana A. Fedash has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Yulia Andrusenko
North Caucasus Federal University
2 shared publications - Alexey Dmitrienko
North Caucasus Federal University
1 shared publication - Alisa Kushchenko
North Caucasus Federal University
1 shared publication - Artem A. Solomyanko
North-Caucasus Federal University
1 shared publication - Danila E. Surenkov1 shared publication
- Dmitry Lukyanov
North Caucasus Federal University
1 shared publication
Latest Publications
- 18 November 2025
- Published by Springer Nature
- p. 31-39
The Theoretical Rationale for Using Quantum Computers to Crack Cryptosystems
- 18 November 2025
- Published by Springer Nature
- p. 31-39
The Theoretical Rationale for Using Quantum Computers to Crack Cryptosystems
- 26 September 2025
- Published by Novosibirsk State Technical University in Digital Technology Security
- No. 3
Research of machine learning methods for detecting SQL injections
This article explores modern machine learning techniques for detecting SQL injections, one of the most common cybersecurity threats. It examines approaches based on neural networks, principal component analysis, and the use of the KNIME platform. The article analyzes the effectiveness of various algorithms and provides recommendations for their implementation in real-world scenarios. The findings demonstrate the potential of machine learning to enhance the security of web applications against SQL injection attacks. Neural networks and PCA-based algorithms have shown significant accuracy in classifying malicious requests. The use of the KNIME platform has simplified the process of model development and testing, making it a promising tool for cybersecurity professionals. Future research directions include integrating these methods with other technologies such as user behavior analysis and machine learning.
- 26 September 2025
- Published by Novosibirsk State Technical University in Digital Technology Security
- No. 3
Research of machine learning methods for detecting SQL injections
This article explores modern machine learning techniques for detecting SQL injections, one of the most common cybersecurity threats. It examines approaches based on neural networks, principal component analysis, and the use of the KNIME platform. The article analyzes the effectiveness of various algorithms and provides recommendations for their implementation in real-world scenarios. The findings demonstrate the potential of machine learning to enhance the security of web applications against SQL injection attacks. Neural networks and PCA-based algorithms have shown significant accuracy in classifying malicious requests. The use of the KNIME platform has simplified the process of model development and testing, making it a promising tool for cybersecurity professionals. Future research directions include integrating these methods with other technologies such as user behavior analysis and machine learning.