The convergence of the Internet of Things (IoT) and cloud computing has created a highly distributed, data-intensive ecosystem that drives innovation across industries. However, the same integration introduces complex cybersecurity risks due to device heterogeneity, scalability requirements, and dynamic threat landscapes 1, 4, 7. Traditional security measures are insufficient in such environments, creating demand for adaptive, intelligent, and proactive defense mechanisms 16, 17. Artificial intelligence (AI) offers powerful capabilities for intrusion detection, anomaly detection, malware analysis, and predictive threat modeling 3, 6, 9. This paper explores how AI techniques ranging from machine learning and deep learning to federated and reinforcement learning are being applied to strengthen IoT–cloud ecosystems against evolving cyberattacks 2, 10, 11. The discussion covers architectural models, real-world deployments, challenges such as adversarial AI, privacy, and compliance, and emerging directions like explainable AI and quantum-safe security 13, 24, 30. The study concludes that AI-driven cybersecurity has transformative potential but requires careful balancing of efficiency, interpretability, and resilience to ensure trust in IoT–cloud ecosystems 19, 23, 31.
Zaka et al. (Thu,) studied this question.