With cyber threats becoming more complex, Cyber- Attack Detection Systems (CADS) are crucial for identifying and preventing attacks. However, traditional methods often fail to detect advanced threats accurately, leading to problems with accuracy, scalability, and reliability. This chapter presents an ensemble- based machine learning framework, referred to Adaptive Weighted Voting Ensemble (AWVE) Model, that leverages the strengths of multiple models to enhance the detection and classification of cyber- attacks. By combining diverse predictive techniques within a unified system, the ensemble approach achieves improved performance, overcoming the shortcomings of individual models. The framework is evaluated using the NSL-KDD dataset, a well- known dataset for network intrusion detection research, to assess its effectiveness in identifying and categorizing various attack types. The results demonstrate that the ensemble framework achieves superior detection rates and classification accuracy across different attack categories while maintaining low false positive rates.