TRIF Fellowship: Privacy-preserving in Android Malware Detection by Investigating User Behavior

With the rapid proliferation of Android devices and the increasing number of malware threats targeting these platforms, it has become crucial to analyse user behavior in malware detection. By analysing user behavior patterns and interactions with their device and applications, it is possible to identify potential malware threats and protect users from malicious activities. User behavior can significantly contribute to Android malware detection in the following ways:

• App Installation and Permissions: Analyzing the apps installed by a user and the permissions requested by those apps can provide valuable insights.
• App Usage Patterns: Monitoring user interactions with apps can help identify anomalies and potentially malicious behavior.
• User Feedback and Reports: User feedback and reports regarding app behavior can be valuable sources of information for malware detection.

The aim of this project is to develop a privacy-preserving framework for Android malware detection by investigating user behavior. The project will focus on enhancing user privacy while effectively identifying and mitigating the risks posed by malicious applications on Android devices.