Enhancing Cybersecurity with AI and Machine Learning: Automated Threat Detection in DevOps and Cloud Environments
Chirag Mavani · Journal of Information Systems Engineering & Management · 2025
With the rapid adoption of DevOps and cloud computing frameworks, traditional cybersecurity methods are increasingly insufficient in addressing the complexities and dynamic nature of modern IT infrastructures. This paper explores the transformative role of Artificial Intelligence (AI) and Machine Learning (ML) in enhancing cybersecurity, particularly in the areas of automated threat detection within DevOps pipelines and cloud environments. By integrating AI-driven solutions, organizations can significantly improve real-time threat identification and mitigation, automating the process of vulnerability scanning, anomaly detection, and incident response. The paper discusses various AI models, such as supervised learning, unsupervised anomaly detection, and reinforcement learning, and their application in addressing specific security challenges in cloud and DevOps environments. Additionally, it investigates the scalability of these AI-driven solutions and the challenges associated with data quality, model biases, and adaptability to emerging threats. Through detailed analysis, case studies, and a conceptual framework, this paper aims to provide a comprehensive overview of the potential and limitations of AI in modern cybersecurity practices, offering recommendations for future research and technological advancements in this field.