Google is using AI for filtering Play Store Applications
With over 2.8 million apps, Google’s Play Store is the biggest app store on the planet. However, trying to make sure that none of those applications are harmful is a massive challenge for Google.
source: Google
To overcome this and sort through the flood of new apps hitting the Play Store every day, Google has revealed that it has developed new detection models by leveraging AI and machine learning algorithms to shut down Android malware. In 2017 alone, Google took down over 700,000 malicious apps that violated it’s Play store policy (a rise of 70 percent compared to 2016), and 100,000 bad developer accounts.
Google used Android’s built-in security and virus detection software, Google Play Protect, to reduce the installation of potentially harmful apps by a factor of 10 and close down over 250,000 copycat apps as well. This software could detect apps that commit fraud, steal information or allow hijacks. Google play protect will be enabled by default on all Android devices and is meant to be a real-time malware scanner that will scan every installed or about-to-be installed app and inform users in case there’s something amiss. However, users can disable Google Protect if they do not want automatic scanning of their device.
Artificial intelligence and machine were used learning to improve the overall experience of browsing through the store for an app or game, simultaneously keeping users safe from bad apps. The role of AI is to detect inappropriate content such as hate speech or violence, and flag those apps so that they could be reviewed more closely by human personnel. It examines privacy and security signals for every app on the Play Store to detect potentially harmful signals on time. Additionally, Machine learning techniques are used to catch apps with abusive content. as a result of which 99% of these apps were identified and rejected before anyone could install them.
Google Play is committed to providing a safe experience for billions of Android users. In 2017, they took down more than a quarter of a million of impersonating apps and the annual installation of potentially harmful apps was reduced by 50 percent.
Despite the new and enhanced detection capabilities, there is a need for improvement so as to simplify the process of hunting for the most safe and apropriate apps for the users. According to Google, the company is “committed to make Google Play the most trusted and safe app store in the world.”
Our take on this
This has most certainly decreased the risk of downloading harmful apps and reduces the number of options to lower the complexity. Further upgradation is required to completely eliminate the irrelevant applications from Google Play Store. The numbers are evidence for the fact that we’ll witness a bigger change in the future.
An avid reader and blogger who loves exploring the endless world of data science and artificial intelligence. Fascinated by the limitless applications of ML and AI; eager to learn and discover the depths of data science.
