2026· International Journal of Data Engineering and Intelligent Computing· Vol 9, pp. 11-21· 0 citations
TL;DR
Results show significant improvement in threat detection accuracy, response time, and overall system resilience, suggesting that AI-based KPS can be a powerful tool in the software security domain.
Abstract
As software systems continue to evolve in complexity, ensuring their security has become an increasingly critical challenge. Traditional security approaches often fail to adapt to dynamic threat landscapes and sophisticated cyber-attacks. This paper presents the design and development of an Artificial Intelligence (AI)-driven Knowledge Processing System (KPS) aimed at optimizing the security of software systems. The proposed system leverages AI techniques such as machine learning, natural language processing, and expert systems to analyze threat patterns, detect anomalies, and suggest real-time mitigation strategies. By integrating continuous learning from security data and contextual knowledge, the system enhances decision-making and predictive capabilities for threat prevention and response. This research highlights system architecture, implementation methodology, and experimental validation to demonstrate the system’s efficacy. Results show significant improvement in threat detection accuracy, response time, and overall system resilience, suggesting that AI-based KPS can be a powerful tool in the software security domain.
A comprehensive review of XAI techniques in industrial cybersecurity, focusing on industrial SOC environments and operational security workflows, and identifies open research directions and opportunities for developing trustworthy, operationally viable, and domain-specific XAI-enabled cybersecurity solutions for industrial environments.
Amr S. Mohamed, Charlotte Fritz, A. M. Saber et al.· 0 citations
This paper organizes the area into a structured taxonomy along five axes: the de-tection capability targeted, the analysis paradigm employed, the agent archi-tecture, the degree of autonomy, and the evaluation methodology.
Andi Xia· Poster Volume 0008 The 2026...· 0 citations
The rapid adoption of Continuous Integration and Continuous Deployment (CI/CD) pipelines has transformed modern software development by enabling frequent releases, automated testing, and accelerated deployment. However, the increased automation and interconnectedness of CI/CD environments have also expanded the attack surface, exposing software delivery pipelines to sophisticated cyber threats such as code injection, supply chain attacks, credential compromise, and malicious configuration changes. Conventional security mechanisms, which rely on static rule-based detection and periodic vulnerability assessments, are often inadequate for identifying evolving attack patterns in dynamic DevSecOps environments. To address these challenges, this paper proposes an AI-driven security framework that integrates Reinforcement Learning (RL)-based intrusion detection into CI/CD pipelines, enabling intelligent, adaptive, and continuous protection throughout the software development lifecycle.The proposed framework combines artificial intelligence techniques with reinforcement learning to continuously monitor pipeline activities, analyze developer and system behavior, detect anomalous events, and dynamically optimize security responses based on environmental feedback. The RL agent learns optimal defense strategies by interacting with the CI/CD environment, allowing it to improve intrusion detection accuracy while minimizing false positives and reducing response latency. Security controls are embedded across key pipeline stages—including source code management, build automation, dependency validation, testing, containerization, artifact management, and deployment—to provide end-to-end protection without disrupting development workflows. Furthermore, automated policy enforcement, vulnerability prioritization, and risk-aware decision-making strengthen the resilience of the software delivery process against both known and zero-day threats.The proposed architecture is evaluated using standard cybersecurity performance metrics, including detection accuracy, precision, recall, F1-score, false positive rate, mean time to detection, and pipeline execution overhead. Experimental results demonstrate that the integration of AI-driven security analytics with reinforcement learning significantly enhances threat detection capability, improves adaptive response to emerging attacks, and maintains software delivery efficiency with minimal computational overhead. Compared with conventional intrusion detection approaches, the proposed framework achieves higher detection performance, faster incident response, and greater robustness against evolving cyber threats.This research contributes a scalable and intelligent DevSecOps security framework that seamlessly integrates AI-based security and reinforcement learning into CI/CD pipelines. By enabling autonomous intrusion detection, adaptive threat mitigation, and continuous software assurance, the proposed solution enhances the security, reliability, and resilience of modern software delivery ecosystems while supporting the growing demands of cloud-native and enterprise software engineering
R. M, H. J. Ramya, Radhika R et al.· International journal of com...· 0 citations
The results showed that embedding explainability in an IDS enhances the human-AI partnership, allowing security analysts to confirm the results of their IDS, mitigate false-positive ambiguity, optimize incident response, and meet regulatory and ethical obligations.
Christian Manna Guimma· Scriptora International Jour...· 0 citations
This paper investigates a secure-by-design engineering process focusing on the initial architectural design and examines the role that AI-powered agents can play in supporting it, as well as the conditions required for their effective and reliable use.
C. Ponsard, Jean-François Daune· International Conference on...· 0 citations
By minimizing false alarms, the proposed framework improves the efficiency of security operations, reduces alert fatigue among cybersecurity analysts, and enables security teams to prioritize genuine threats more effectively.
Reily Kaium, Lizi Alasa, K. Robert et al.· The Eastasouth Journal of In...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
