AI-Enhanced DevSecOps for Secure and Compliant CI/CD Pipelines
pdf

Keywords

DevSecOps
CI/CD Security
Explainable AI
Federated Learning
Adversarial Attacks
Compliance

How to Cite

Jajanidze, I. (2026). AI-Enhanced DevSecOps for Secure and Compliant CI/CD Pipelines. International Scientific-Practical Conference: „Modern Challenges and Achievements in Information and Communication Technologies“ Transactions, 4, 407-409. https://papers.4science.ge/index.php/mcaaict/article/view/443

Abstract

Continuous Integration and Continuous Deployment (CI/CD) pipelines have revolutionized software delivery by enabling rapid iterations and reducing release cycles. However, this acceleration of deployment also magnifies risks: insecure code can propagate more quickly, compromised dependencies can infiltrate multiple environments, and automated release processes broaden the attack surface. Traditional, rule-based defenses struggle in such dynamic environments.

This paper introduces an AI-Enhanced DevSecOps framework that strengthens pipeline security through the integration of Explainable AI (XAI), Federated Learning (FL), adversarially resilient malware detection, and AI-augmented defenses against social engineering. By combining these techniques with DevSecOps principles, organizations can achieve both resilience and compliance with regulations such as the GDPR, NIST SP 800-53, and the EU’s Digital Operational Resilience Act (DORA). Real-world case studies, including SolarWinds, Mirai Botnet, and phishing simulation research, demonstrate the necessity and practical benefits of such integration. Results highlight measurable improvements in detection accuracy, mean time to resolution, and overall trust in automated security decisions.

pdf

References

I. Jajanidze, The Use of Artificial Intelligence in CI/CD Systems, Georgian Scientific Journals: Computer Science & Telecommunications, 2025.

C. Cath, et al., Artificial Intelligence and the ‘Good Society’: The US, EU, and UK Approach, Science and Engineering Ethics, vol. 24, no. 2, pp. 505–528, 2018.

D. Gunning, et al., XAI-Explainable Artificial Intelligence, Science Robotics, vol. 4, no. 37, 2019.

H. Yang, et al., Federated Machine Learning: Concept and Applications, ACM Transactions on Intelligent Systems and Technology, vol. 10, no. 2, pp. 1–19, 2019.

D. Ucci, L. Aniello, and R. Baldoni, Survey of Machine Learning Techniques for Malware Analysis, Computers & Security, vol. 81, pp. 123–147, 2019.

A. Bichnigauri, I. Kartvelishvili, O. Shonia, D. Bichnigauri, and O. Gudadze, Strengthening Cyber Defenses – The Crucial Role of Phishing Simulation in Modern Security Strategies, Defence and Science, no. 3, 2024.

I. Kartvelishvili, G. Kuchava, Optimization of Software Delivery in DevOps with CI/CD, Proceedings of the International Scientific-Practical Conference, Georgian Technical University, 2024.