Intrusion Detection Using Machine Learning for Security and Privacy in Humanitarian Aid System

Intrusion detection systems (IDS) are crucial for ensuring the integrity and security of humanitarian aid systems to secure sensitive data. However, deploying IDS in humanitarian aid systems can be challenging due to limited infrastructure, lack of cybersecurity expertise, and data complexity. This study proposes several machine learning algorithms, including Gaussian Naïve Bayes, decision tree, random forest, support vector machine, logistic regression, gradient boosting, and artificial neural network, on the KDDCUP-99 dataset. The results showed excellent performance, with decision tree and gradient boosting achieving 100% accuracy, random forest and support vector machine obtaining 99% accuracy, and artificial neural network achieving 99.84% accuracy rate. This study also compares the proposed models with the state-of-the-art methods to provide a performance benchmark for the IDS. Future works can focus on ensemble and deep learning models to improve the performance of IDS in humanitarian aid systems.