Machine learning is a promising technology for network intrusion detection systems. There is a wide variety of machine learning algorithms whose results seem complementary, but determining which result is true is difficult because models lack explainability. Our system intends to reconstruct attack patterns from a set of unsupervised learning models' outputs, and show them to security analysts. Therefore, we introduce an explainable-by-design system to detect network attacks, and evaluated its accuracy on the CSE-CIC-IDS2018 dataset.