Explainable Artificial Intelligence in Ethical Hacking: Bridging Trust, Transparency, and Cyber Security Effectiveness

Abiola O. Akinyemi

doi:10.56201/wjimt.v10.no2.2026.pg61.68

📄 Download Paper

Explainable Artificial Intelligence in Ethical Hacking: Bridging Trust, Transparency, and Cyber Security Effectiveness

Abiola O. Akinyemi

Abstract

Artificial Intelligence (AI) has become a key part of modern ethical hacking and penetration testing. It significantly improves the automation, scalability, and effectiveness of cyber security assessments. However, as we rely more on complex machine learning and deep learning models, we face a major challenge: the lack of transparency in AI-driven decision-making. Many AI- powered ethical hacking systems act as black boxes, limiting human understanding and trust in discovering vulnerabilities and creating attack paths. This paper addresses this issue by proposing a framework for Explainable Artificial Intelligence in ethical hacking. This framework incorporates transparency into AI-powered penetration testing workflows. Using a design science research method, the study develops a layered conceptual structure that combines AI-based ethical hacking, explainability methods, and human feedback. A structured evaluation combines simulated penetration testing, quantitative performance analysis, and trust assessment focused on humans. The results show that adding explainability notably improves analyst trust and decision confidence while keeping a high level of cyber security effectiveness. This work offers a new interdisciplinary approach that supports the adoption of trustworthy AI in ethical hacking and modern cyber security defense.

Keywords

Explainable Artificial IntelligenceEthical HackingCybersecurityPenetration TestingTrustworthy AIXAI

References

Abdul, A., et al. (2022). Human-centered explainable AI: A survey. ACM Computing Surveys, 54(9). Almukaynizi, M., et al. (2021). Autonomous penetration testing using reinforcement learning. IEEE Security & Privacy, 19(4), 72–81. Arrieta, A. B., et al. (2021). Explainable artificial intelligence: Concepts, taxonomies, and challenges. Information Fusion, 58, 82–115. Buczak, A. L., & Guven, E. (2022). A survey of data mining and machine learning methods for cybersecurity intrusion detection. IEEE Communications Surveys & Tutorials, 24(2), 1153–1176. European Commission. (2022). Ethics guidelines for trustworthy AI. Floridi, L., et al. (2022). AI ethics for cybersecurity governance. Nature Machine Intelligence, 4, 895–903. Hevner, A. R., et al. (2004). Design science in information systems research. MIS Quarterly, 28(1), 75–105. Husari, G., et al. (2021). TTPDrill: Automatic cyber-attack emulation. IEEE Transactions on Dependable and Secure Computing, 18(2), 987–1001. IEEE. (2022). Ethically Aligned Design. NIST. (2023). AI Risk Management Framework (AI RMF 1.0). Peffers, K., et al. (2021). Design science research methodology. Journal of Management Information Systems, 38(4), 1185–1213. Zhang, Y., et al. (2023). AI-based vulnerability detection in complex networks. Computers & Security, 124, 102972. Zhang, H., et al. (2024). Explainable AI for trustworthy cybersecurity systems. IEEE Transactions on Artificial Intelligence, 5(1), 34–48. Zhang, L., et al. (2025). Human-in-the-loop explainable AI for security analytics. ACM Transactions on Privacy and Security, 28(1).

Explainable Artificial Intelligence in Ethical Hacking: Bridging Trust, Transparency, and Cyber Security Effectiveness

Abstract

Keywords

References

More Articles from WORLD JOURNAL OF INNOVATION AND MODERN TECHNOLOGY