In this research, we inquest the application of machine learning models in the realm of cyber security for intrusion detection. The rising complexity and number of cyber threats need the development of innovative and effective intrusion detection systems. Machine learning brings a revolution in diverse domains which includes cyber security. This research paper appraises the potential of the application of a machine learning-based model to enhance intrusion detection in network traffic. The proposed model comprehends a weighted ensemble of multiple ML classifier algorithms and can detect binary classification as well as multi-class classification. NSL-KDD dataset, a renowned dataset for cyber security assessment, was used for this research. The findings of this research demonstrate that using ML approaches for intrusion detection attains a high precision and minimizes false positives. The weighted ensemble model performs superior to other ensemble techniques. In conclusion, our findings of this study show that the proposed model achieves 98% accuracy in binary classification and 99% accuracy in multi-class classification. This result demonstrates that our model can be employed effectively for detecting intrusive activity in cyberspace and also can give a potential answer to cyber security concerns of this day.