The adoption of Artificial Intelligence (AI) as a part of DevOps pipelines has proven to be a disruptive factor in improving software security. Using AI, organizations will be able to scale continuous vulnerability scanning and anomaly detection to automate their DevOps environments and make them more resilient and efficient. The machine learning and deep learning AI models can scan through large volumes of data in real-time to detect vulnerabilities and potential threats that other methods might fail to detect. In this paper, we will discuss how AI can be implemented in DevOps work, and how it can be used to simplify security processes, improve detection accuracy, and decrease the response time. The results also shed light on the massive influence of AI on the automation of security patches, real-time monitoring, and predictive threat analysis. It also found that there are obstacles to the adoption of AI, such as resource limitations and model optimization. Generally, AI-based surveillance should be used in order to have a positive impact on the security level in the contemporary DevOps setting and mitigate the appearance of new threats on a routine basis.
Patel et al. (2025) studied this question.