Android Malware Detection Using Machine Learning And Permissions — Complete Documentation & Simulation

Overview & System Context

Android Malware Detection Using Machine Learning And Permissions: Comprehensive Web-Sourced Technical Investigation Exhaustive Research Dossier · Pure Web-Scraped Content: ~633 Words · Real Software Screenshots: 3 1. Executive Overview & Technical Background Project at IIITD under the course CSE343 : Machine Learning under the guidance of Professor Anubha Gupta As the android market continues to expand, so does the prevalence of malicious apps. According to ZDNet , as many as 10%-24% of apps available on the Play store could be malicious in nature. These apps may appear innocuous at first glance, but they can wreak havoc on a user’s system in a variety of harmful ways. Unfortunately, current methods for detecting malware are both resource-intensive and exhaustive, and they struggle to keep up with the rapid pace at which new malware is being developed.

2. System Architecture & Core Working Principles Despite the growing threat of malware, there is still no reliable and robust method for detecting malicious applications. However, with the increasing use of machine learning in various fields, we believe that this issue can be addressed through the application of machine learning techniques. Our project aims to conduct a thorough and systematic investigation into the use of machine learning for malware detection, with the ultimate goal of developing an efficient ML model capable of accurately classifying apps as either benign (0) or malware (1) based on their requested permissions. This study Proposes: Prerocessing, Visualization and Analysis: The data is first imported from a CSV file and loaded into a dataframe for ease of use. The necessary attributes are then extracted from the dataset. To gain a better understanding of the data, several plots are generated. The data is checked for null or missing values, and any such values are replaced with the mean of the corresponding column. The distribution of malware and benign applications across various settings is then analyzed, and the results are visualized through a series of plots created using Matplotlib and Seaborn .

3. Software Implementation, Frameworks & Protocols The EDA for the Android Permission Dataset provided valuable insights into the relationships between different features in the dataset and helped us identify the most important features for predicting the app rating. It also provided a foundation for further analysis using machine learning techniques.

After preprocessing the data, it is split into testing and training sets at an 8:2 ratio . We attempted both under and oversampling techniques on the dataset, but the results were not promising. We then applied various classifiers, including logistic regression, decision trees, and Naive Bayes, but the outcomes were unsatisfactory. Upon further inspection of the dataset, we discovered that it contained several multivariate data tables, which required us to apply PCA to each dataset. We plotted the variance percentage after using PCA and chose to use the inverse transform. We then applied Random Forest to the dataset, which resulted in a significant improvement in accuracy. We then used the boosting approach to further increase prediction accuracy, both on an unsampled dataset and on one with reliable features selected. The results showed that the model was improving. Finally, we applied SVM and MLP to the final dataset and achieved our best results. When comparing the results obtained after feature selection and boosting , we can see that we have made significant progress and achieved our final accuracy.

4. Practical Deployment, Analysis & Case Studies As we can see that sampling is not effective in our case so move forward with unsampled data only. By looking at the result all the three models performs more or less the same with Random Forest with Accuracy of 86%. As we seen in the Tabulation that, Accuracy follows the order as follow: Random Forest > MLP > SVM 5. Performance Evaluation & Extended Technical Observations [ 2 ] An Efficient Android Malware Prediction Using Ensemble Machine Learning Algorithms Leveraging the power of Machine Learning as a tool, we delve into the realm of app permissions to discern the true nature of applications, whether they harbor malicious or benign intent. By analyzing and predicting based on these permissions, we unlock valuable insights to safeguard users in the digital landscape.

Figure 1: Diagnosing and Mitigating Domain Shift in Permission-Based Android ... Figure 2: Malware Detection in Android Mobile Devices by Applying Swarm ... Figure 3: Graph Approach for android malware detection using machine learning ... Harvested Online Documentation & Reference Sources • https://github.com/Findcoding/Android-Malware-Detection-System-Using-Machine-Learning