A method of generating data for further training artificial intelligence models aimed at solving cybersecurity problems

Chernihivskyi, Ivan та Kriuchkova, Larysa (2025) A method of generating data for further training artificial intelligence models aimed at solving cybersecurity problems Workshop on Cybersecurity Providing in Information and Telecommunication Systems (4145). с. 246-256. ISSN 1613-0073

Текст I_Chernihivskyi_L_Kriuchkova_CPITS_4145_2025_FITM.pdf Download (894kB)

Анотація

Artificial intelligence-based cyberattacks are becoming a significant challenge in cybersecurity. Cybercriminals are using artificial intelligence to increase the sophistication and impact of their attacks, making them increasingly complex and difficult to detect. Threats driven by artificial intelligence can automate vulnerability detection, create convincing phishing schemes, and even adapt in real time to bypass security measures. The dynamic development of artificial intelligence necessitates a proactive and innovative approach to cybersecurity. The paper presents the dynamics of the growth of cybercrime, in particular with the use of AI, and justifies the need to involve AI in solving cybersecurity problems. The method of generating training data for further training AI models proposed, which provides: specialization of a specific AI model to detect the main signs of viral activity in the provided digital traces; improvement of the quality of AI responses; reducing response time to cybersecurity incidents. Presenting digital traces in a tabular format with pre-filtering of digital traces based on a relational artifact table allows reducing the number of elements required for further research.

Тип елементу :	Стаття
Ключові слова:	artificial intelligence; neural network models; malware; digital footprints; cyberattacks; cybersecurity; AI model training
Типологія:	Статті у базах даних > Scopus (без квартилю)
Підрозділи:	Факультет інформаційних технологій та математики > Кафедра інформаційної та кібернетичної безпеки ім. професора Володимира Бурячка
Користувач, що депонує:	Павло Миколайович Складанний
Дата внесення:	20 Трав 2026 08:59
Останні зміни:	20 Трав 2026 08:59
URI:	https://elibrary.kubg.edu.ua/id/eprint/57479

Actions (login required)

Перегляд елементу