AI Driven Real Time Cybersecurity Threat Detection in Edge and Cloud Architectures

The rapid growth of digital infrastructures such as cloud computing, Internet of Things (IoT), and edge networks has significantly increased the complexity and scale of cyber threats. Traditional cybersecurity mechanisms, primarily based on signature and rule-based detection, are increasingly ineffective against sophisticated and evolving attacks. Artificial Intelligence (AI) has emerged as a powerful solution to address these limitations by enabling real-time threat detection, anomaly analysis, and automated response. This paper presents a comprehensive study of AI-driven cybersecurity systems with a focus on intrusion detection and threat mitigation in edge–cloud environments. The paper reviews recent machine learning and deep learning techniques, discusses explainable and lightweight AI models suitable for resource-constrained devices, analyzes emerging AI-related threats such as adversarial attacks and prompt injection and outlines future research directions. The study demonstrates that AI-based cybersecurity systems significantly enhance detection accuracy and adaptability, making them essential for securing modern distributed networks.