OTENTIALS OF ARTIFICIAL INTELLIGENCE IN DETECTING AND PREVENTING PHISHING AND CYBER ATTACKS
DOI:
https://doi.org/10.28925/2663-4023.2025.29.840Keywords:
malware, generative artificial intelligence, cyber threats, phishing attacks, automated responseAbstract
This paper examines the dual role of artificial intelligence (AI) in today’s cybersecurity landscape, highlighting its capacity to both enhance cyberattacks and support the development of effective defense mechanisms for information systems. The study analyzes the increasing complexity of threats driven by advancements in machine learning, natural language processing, and generative AI (GenAI), which enable attackers to automate, improve the accuracy of, and disguise attacks, including phishing, malware creation, and the use of deepfakes. This research explores how AI-based solutions can strengthen cybersecurity by detecting potential threats in real time through machine learning, NLP, and image recognition techniques. Special attention is given to the necessity of integrating AI with human oversight, emphasizing the importance of combining automated responses with expert analysis to effectively mitigate risks and adapt to emerging challenges. The paper reviews a range of modern tools and techniques used to execute AI-assisted cyberattacks, such as ChatGPT, WormGPT, FraudGPT, and Morris 2.0, demonstrating their capabilities in crafting convincing fraudulent scenarios and adaptive malicious software. In parallel, it examines AI-powered technological solutions designed to detect and counter cyber threats in real time. It describes the functionality of systems like Darktrace Antigena, Cylance Endpoint Security, Splunk, Exabeam, IBM QRadar, and Microsoft Sentinel, which leverage behavioral analysis, machine learning, and image recognition for proactive anomaly detection, automated incident response, and overall security enhancement. This study illustrates how AI is transforming cybersecurity by providing adaptive and proactive strategies to combat emerging cyber threats. By exploring contemporary AI applications, it demonstrates how AI can reshape cybersecurity by offering proactive and adaptive approaches to counter cyberattacks and protect sensitive data.
Downloads
References
Zellers R., Holtzman A., Bisk Y., Farhadi A., Choi Y. Defending Against Neural Fake News // Advances in Neural Information Processing Systems (NeurIPS 2019). – 2019. – С. 9054–9065. – URL: https://papers.nips.cc/paper/9106-defending-against-neural-fake-news.pdf
Bostrom N., Yudkowsky E. (eds.) Global Catastrophic Risks. – Oxford: Oxford University Press, 2008. – С. 308–345.
Kenneth R. Feinberg Center for Catastrophic Risk Management and Compensation. Insuring Catastrophic Cyber Risk. – 2025.
Shevlane T. An Early Warning System for Novel AI Risks // Google DeepMind. – 2024. – URL: https://deepmind.google/discover/blog/an-early-warning-system-for-novel-ai-risks/
Scanlon M., Breitinger F., Hargreaves C., Hilgert J.-N., Sheppard J. ChatGPT for Digital Forensic Investigation: The Good, the Bad, and the Unknown // Forensic Science International: Digital Investigation. – 2023. – Vol. 46. – Article 301609.
Tihanyi N., Ferrag M.A., Jain R., Debbah M. CyberMetric: A Benchmark Dataset for Evaluating Large Language Models Knowledge in Cybersecurity. – 2024.
Main Directorate of Intelligence of the Ministry of Defence of Ukraine. Defence Intelligence of Ukraine Thwarted a Provocation by Russian Pranksters Against Baykar Defence CEO Haluk Bayraktar. – URL: https://gur.gov.ua/content/hur-mo-zirvalo-provokatsiiu-rosiiskykh-prankeriv-proty-heneralnoho-dyrektora-kompanii-baykar-defence-khaliuka-bairaktara.html
Begou N., Vinoy J., Duda A., Korczynski M. Exploring the Dark Side of AI: Advanced Phishing Attack Design and Deployment Using ChatGPT. – 2023.
Saha Roy S., Naragam K.V., Nilizadeh S. Generating Phishing Attacks Using ChatGPT. – 2023.
Islam R. Generative AI, Cybersecurity, and Ethics. – George Mason University, Fairfax, Virginia, United States, 2025.
Piconese F., Hakkala A., Virtanen S., Crispo B. Deployment of Next Generation Intrusion Detection Systems against Internal Threats in a Medium-sized Enterprise, 2020.
Šuškalo D., Morić Z., Redžepagić J., Regvart D. Comparative Analysis of IBM QRadar and Wazuh for Security Information and Event Management, 2023.
Happe A., Cito J. Getting Pwn’d by AI: Penetration Testing with Large Language Models
The EU Artificial Intelligence Act. – URL: https://artificialintelligenceact.eu/
Kelley D. WormGPT – The Generative AI Tool Cybercriminals Are Using to Launch Business Email Compromise Attacks // SlashNext. – 2023.
Krishnan R. FraudGPT: The Villain Avatar of ChatGPT // Neterich. – 2023.
Morris Worm II. What Is Known About Computer Viruses in the Age of AI // ForkLog UA. – 2024.
Helping Ethical Hackers Use AI in 50 Lines of Code or Less. – URL: https://hackingbuddy.ai/
What is Cylance Endpoint Security? – URL: https://docs.blackberry.com/en/unified-endpoint-security/blackberry-ues/overview/What-is-Unified-Endpoint-Security
Automate Threat Response in Microsoft Sentinel with Automation Rules. – URL: https://learn.microsoft.com/en-us/azure/sentinel/automate-incident-handling-with-automation-rules?tabs=onboarded
QRadar overview. – URL: https://www.ibm.com/docs/en/qsip/7.5?topic=started-qradar-overview
Dalalah D., Dalalah M. The false positives and false negatives of generative AI detection tools in education and academic research: The case of ChatGPT. – 2023.
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Максиміліан Яковлев, Володимир Любчак
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
