Network intrusion detection plays an important role in protecting computers and networks against unauthorized access, attacks, and malicious activities. As the effectiveness of cyber threats continues to evolve, the need for advanced and robust detection systems has become critical. This study investigates the use of technology in attack detection, focusing on the integration of various base-classifiers and meta-classifiers. Among a total of 13 base-classifiers using different algorithms, the three base-classifiers that provided the best accuracy were selected as meta-classifiers. Using different combinations of base-classifiers and meta-classifiers, the overall accuracies were compared and certain trends were observed. After the implementation of stacked classifiers, the best accuracy of 99.91% was observed with all base-classifiers combined with the meta-classifier CatBoost.