Feel free to contribute on Github
Android is the most popular operating system today. The popularity of the Android platform has also attracted malware developers towards it. Malware attack is a challenging issue among the Android user community. So it is necessary to make the platform safe for users by providing a defence mechanism against malware.
Traditional virus detection relies on the use of signatures. The problem with signatures alone is that new types of viruses such as polymorphic ones can mutate their code, making signature generation difficult or impossible. By utilising a machine learning approach, we can detect malware without explicit knowledge of their presence.
LibreAV is an attempt to detect malware on Android devices using a machine learning approach that is powered by TensorFlow. We use a two-layer neural network trained with a carefully selected set of features. The neural network is tuned in such a way that it performs efficiently on mobile devices where computational resources are limited. Tests show that LibreAV performs efficiently and effectively even on low-end mobile devices. With LibreAV, you can scan all the installed apps in your device in a matter of seconds. It also has a real-time scan feature which alerts you whenever an app is installed or updated.
We welcome contributions from your side. That is why we released it as open-source under GNU GPLv3. The motivation behind LibreAV is to make the digital world a safe and secure place. LibreAV is expected to be supported by the open-source community. So your contributions are very important to us.
Check out LibreAV, let's fight malware together.
Android is a trademark of Google LLC.