Malware infestations have increased with the rise of mobile devices, notably Android smartphones. Our work fixes this issue by improving Android security using Decision Trees, SVMs, RFs, and KNNs. A dependable Android malware protection solution is one of our key goals. We will test these machine learning methods against diverse illnesses. Android smartphones are becoming increasingly popular, raising security concerns. Emerging solutions are needed to detect emerging dangers. Machine learning algorithms that recognize and anticipate patterns may replace Android security. Decision Tree (DT), k-nearest Neighbors (KNN), Random Forest (RF), and Support vector Machine (SVM) algorithms helped us construct a strong malware detection system. We rank Android malware detection machine-learning approaches on efficiency, accuracy, and speed. This tip should assist choosing and implementing Android security machine-learning solutions. Decision trees are open-source, random forests utilize ensemble learning, support vector machines excel in probabilistic classification, and KNN detects Android infections best using similarity patterns. A comparison study can provide the finest security solution. By the conclusion it secured Android using machine learning and set the framework for mobile device security research. Android security weaknesses must be fixed to keep devices safer against future attacks.