Comprehensible AI in Cyber Security: Bridging the Trust Gap

Abstract Artificial Intelligence (AI) has become a pivotal component of modern cybersecurity, supporting real-time threat detection, anomaly recognition, and automated incident response. Despite its capabilities, the black-box nature of many AI models—especially deep learning and complex machine learning algorithms—has introduced a significant trust gap between machine-generated decisions and human interpretation. Comprehensible AI has emerged as a key approach to bridging this divide by offering transparency, interpretability, and accountability within AI-driven cybersecurity systems. This paper examines the integration of AI in cybersecurity, focusing on how explainability enhances trust, strengthens threat intelligence, and supports regulatory compliance. Through a comprehensive literature review and methodological evaluation, the study investigates current challenges and recent advancements in the application of AI to cybersecurity. Findings demonstrate that incorporating explainable AI not only improves threat detection capabilities but also promotes effective collaboration between human analysts and AI systems. The paper concludes by outlining future directions for research aimed at improving model interpretability without sacrificing performance. Keywords Comprehensible AI, Cybersecurity, AI Transparency, AI Interpretability, AI-driven Threat Detection, Anomaly Detection, Machine Learning Security, Trustworthy AI