EXPLAINABLE ARTIFICIAL INTELLIGENCE FOR CYBERSECURITY THREAT DETECTION: IMPROVING TRUST AND TRANSPARENCY IN INTELLIGENT SECURITY SYSTEMS

The rapid evolution of cyber threats has increased the demand for intelligent security systems capable of detecting sophisticated attacks in real time. Artificial Intelligence (AI) has significantly enhanced intrusion detection, malware classification, phishing detection, and anomaly identification through advanced machine learning algorithms. However, many AI-based cybersecurity models operate as "black boxes," making their decision-making processes difficult to interpret. This lack of transparency reduces user trust and limits practical deployment in critical infrastructures. Explainable Artificial Intelligence (XAI) addresses this challenge by providing understandable and interpretable explanations for AI-generated decisions. This paper investigates the role of Explainable Artificial Intelligence in modern cybersecurity, presents a comprehensive XAI-based threat detection framework, discusses recent advancements, evaluates existing challenges, and explores future research directions. The proposed framework combines deep learning, explainability techniques, attention mechanisms, and human-centered visualization to improve transparency while maintaining high detection accuracy. The study concludes that Explainable AI represents an essential component of trustworthy cybersecurity systems capable of supporting both automated and human-assisted security operations.