Intrusion detection and blockchain technology have been extensively studied to enhance data privacy and identify current and potential cyber attacks. In this approach, machine learning algorithms can identify complicated malicious occurrences simultaneously by protecting data privacy. This model is utilized to offer more security and privacy in the cloud to protect net-works. This research proposes an innovative Intrusion Detection System imposing blockchain technology which employs consensus mechanisms and compares different machine learning methods including XGBoost, Random Forest, Decision Tree, and Extra Tree. This system is developed to enhance data privacy, security, and protect Internet-of-Things networks. The utilization of ant colony optimization further improves accuracy during real-time data analy-sis. The aim of the study is to extend the application of machine learning for network intrusion detection and to conduct a comparative analysis of the proposed ant colony algorithms with other existing studies in terms of accuracy, recall, and precision measures. The high accura-cy and strong intrusion detection capability of the model are verified through experimental evaluations using datasets such as NSL-KDD and CICIDS2017. Proposed system shows ef-fectiveness by using creative technology integration for mitigating cyber security risks. The experimental result shows that a machine learning algorithm using ant colony optimization achieves 99% accuracy. This model represents a significant progression towards addressing a resilient solution for cyber security challenges and to tackle new cyber threats.