Intrusion Detection using Explainable Machine Learning Techniques
Rishikant Mallick, Smriti Rout, Soumyabrata Biswas, Lalit Kumar Vashishtha, Santosh Kumar Sahu · 2023
With the rise in complex cyber threats, there is a pressing need for accurate and interpretable methods to detect intrusions effectively. This research investigates the fusion of explainable machine learning techniques with intrusion detection, aiming to improve both detection accuracy and the ability to interpret model decisions. The study involves the utilization of various explainable machine learning algorithms, such as LIME (Local Interpretable Model-Agnostic Explanations) and SHAP (SHapley Additive exPlanations), to create models that not only predict intrusions but also provide insights into the features influencing these predictions. The proposed approach is tested on a benchmark intrusion detection dataset, and its performance is compared with traditional machine learning methods. The results demonstrate that the explainable machine learning-based intrusion detection approach achieves competitive detection accuracy while also offering valuable explanations for each prediction. This enhanced interpretability aids cybersecurity experts in comprehending why certain instances are flagged as intrusions. By combining accuracy and transparency, this research contributes to the development of more reliable and understandable intrusion detection systems, thereby bolstering cyber defense strategies in an increasingly intricate digital landscape.