Malware detection using different machine learning models

The proliferation of malware seriously threatens user security and privacy. The primary objective of this research is to develop and evaluate machine learning models to detect malware accurately. The objective is to assess the performance of various classification algorithms against a single user-specific dataset to determine which models are most suitable for use in real-world scenarios. The project commences with the collection of data and preprocessing of malicious and non-malicious applications. The data is then carefully chosen to train and test the models using modern feature extraction and preprocessing techniques. Various classification techniques are employed, including Decision Trees (DMTs), Support Vector Machines with various kernels (SVM), Logistics Regression (LGRs), KNNs (KNNs), and Sequential Neural Networks (SNNs). The performance of each model is measured in terms of precision, recall and F1 score through meticulous experimentation and review of the results. The results provide valuable insights into the pros and cons of each method when it comes to Android virus detection, with the SNN being the most accurate.