Artificial intelligence in Cybersecurity

Artificial Intelligence has become an important research area in cybersecurity because of its ability to analyze large volumes of data, identify patterns, and support the detection and analysis of cyber threats. Machine Learning, Deep Learning, Explainable Artificial Intelligence, and emerging Large Language Models have been investigated for applications including intrusion detection, malware detection, phishing detection, anomaly detection, and security analysis. The review shows that AI can provide valuable capabilities for cybersecurity, but its effectiveness depends on training-data quality, model selection, evaluation methods, and the ability to adapt to changing threats. AI systems also introduce their own security risks. Adversarial Machine Learning research demonstrates that AI models can be targeted through different forms of attacks, including evasion, poisoning, privacy, and misuse attacks. Therefore, the future of AI-based cybersecurity should focus not only on improving detection performance but also on developing systems that are robust, explainable, privacy-aware, adaptable, and secure. Continued research in these areas can contribute to the development of more trustworthy AI-based cybersecurity solutions and improve the ability of organizations to respond to an evolving cyber-threat landscape.

1. Salem, A. H., Azzam, S. M., Emam, O. E., et al.: Advancing cybersecurity: a comprehensive review of AI-driven detection techniques. Journal of Big Data 11, 105 (2024). 2. Pawlicki, M., Pawlicka, A., Kozik, R., et al.: The survey on the dual nature of xAI challenges in intrusion detection and their potential for AI innovation. Artificial Intelligence Review 57, 330 (2024). 3. Vassilev, A., Oprea, A., Fordyce, A., Anderson, H., Davies, X., Hamin, M.: Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations. NIST AI 100-2e2025. National Institute of Standards and Technology (2025). 4. National Institute of Standards and Technology: Cybersecurity Framework Profile for Artificial Intelligence. NIST (2025). 5. Selected recent systematic-review literature on Large Language Models and cybersecurity applications, including vulnerability detection, malware analysis, intrusion detection, and phishing detection. 6. Selected recent literature on Machine Learning-based intrusion detection systems, including studies comparing ML/DL methods, datasets, evaluation metrics, and cybersecurity challenges.