Open source platforms such as Android, always face security threats. However, Google has been working on the ground to out do malware and suspicious apps on its Play Store. Several platforms have deployed Machine learning and AI to furnish various tasks. The most radical propensity of machine learning is its tendency to improve each time it carries out a task.
Google has been using AI and machine learning to identify suspicious apps on Android's app store, Play Store. Google uses a technique known as 'peer grouping' to secure the Play Store. Peer grouping creates segments of similar kinds of apps and then runs a reconnaissance to look out for ones with suspicious elements. For example, if Google is looking through a group of photo editing apps it would sort out apps that require irrelevant permissions such as accessing microphone or location service since there is no for such an app to access a smartphone's microphone or location. Google then keeps a close look at such apps and identifies them to avoid any discrepancy.
Google's security and privacy team expert Martin Pelikan explained further, "We focus on signals that can negatively affect user privacy, such as permission requests that are not related to core app functionality, and the actual, observed behaviors. For example, a flashlight app might not need access to address book of the user or the precise hardware identifier of a user's phone. The same might hold for many other apps, such as 'mirror' apps that turn on a device's front-facing camera."
It seems like there is no getting away for malware from Google's machine learning and AI.