Through the use of Machine Learning to detect apps that impersonate, have inappropriate content or malware, Google removed over 700,000 rogue apps from the Google Play Store, taking 100,000 repeat offender developers along with them. The injection of ML can find patterns that detect bad behaving apps quicker than human inspectors, resulting in a 70% increase in removing of apps from the Play Store over the previous year.
Not only did we remove more bad apps, we were able to identify and action against them earlier. In fact, 99% of apps with abusive contents were identified and rejected before anyone could install them.
The end result is that the Play Store, while still not perfect, is a far safer place than it was this time last year and it will only get better as the Machine Learning models get smarter.
Google tended to focus on three types of offending apps in 2017.
- Copycat apps where the app is attempting to deceive users by impersonating famous apps is one of the most common violations.
- Inappropriate content such as pornography, extreme violence, hate and illegal activities. Google points out that ML proved to be invaluable as the models would detect the content and human reviewer would make the final decision on the app.
- Potentially Harmful Apps… or Malware. PHAs are a type of malware that can harm people or their devices — e.g., apps that conduct SMS fraud, act as trojans, or phishing user’s information.
By their own admission, Google knows that there are still ways for rogue developers to get their apps into the Play Store. It is getting harder, and will continue to do so as the ML models continue to be improved.
You can read the full blog post over at Google Android Developers Blog site.