Explainable AI for cyber security. Improving transparency and trust in intrusion detection systems
Akpan Itoro Udofot, Omotosho Moses Oluseyi Omotosho Moses Oluseyi, Edim Bassey Edim · International Journal of Advances in Engineering and Management · 2024
In recent years, the integration of Artificial Intelligence (AI) in cybersecurity has significantly enhanced the capabilities of Intrusion Detection Systems (IDS) to detect and mitigate sophisticated cyber threats. However, the increasing complexity and opaque nature of AI models have led to challenges in understanding, interpreting, and trusting these systems. This paper addresses the critical issue of transparency and trust in IDS by exploring the application of Explainable AI (XAI) techniques. By leveraging XAI, we aim to demystify the decision-making processes of AIdriven IDS, enabling security analysts to comprehend and validate the system's outputs effectively. The proposed framework integrates model-agnostic XAI methods, such as Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP), with state-of-the-art IDS algorithms to improve both interpretability and performance. Through comprehensive experiments on benchmark datasets, we demonstrate that our approach not only maintains high detection accuracy but also enhances the explainability of the model's decisions, thereby fostering greater trust among end-users. The findings of this study underscore the potential of XAI to bridge the gap between AI’s advanced capabilities and the human need for understanding, ultimately contributing to more secure and reliable cyber defense systems.