The increasing dependence on digital networks has resulted in a significant rise in cyber threats that can affect the confidentiality, integrity, and availability of information systems. Intrusion Detection Systems (IDS) play a vital role in identifying suspicious activities within network environments. While machine learning techniques have improved intrusion detection accuracy, many models function as black-box systems, making their predictions difficult to interpret. This lack of transparency limits user confidence and practical adoption in security operations.

To overcome this challenge, this research presents an Explainable Artificial Intelligence (XAI)-driven intrusion detection framework that combines machine learning with interpretable decision analysis. The proposed model utilizes the NSL-KDD dataset for training and evaluation and employs the Gradient Boosting classification algorithm to distinguish normal network behavior from malicious traffic. SHAP (Shapley Additive Explanations) is integrated to explain how individual features contribute to classification outcomes. Experimental findings demonstrate that the system effectively detects cyber-attacks while providing clear insights into the reasoning behind each prediction. The proposed framework enhances both detection capability and decision transparency, making it suitable for real-world cybersecurity applications.

Keywords: Intrusion Detection System, Explainable Artificial Intelligence, Machine Learning, SHAP, Network Security, Cybersecurity.