Cybersecurity and Google’s Play Store are no strangers. Over its almost decade-long existence, the Play Store has been plagued by bugs and malicious mobile app developers much more so than its rival, Apple’s App Store. Andrew Ahn, Product Manager of Googe Play, recently discussed how the tech titan’s increased cyber safeguarding measures led to the removal of over 700,000 apps in 2017.
If that figure doesn’t astound you, maybe putting it in perspective with the previous year will: 2017 marked a 70 percent increase in app removals compared to 2016. But sheer numbers alone don’t objectively tell whether this was a sign of progress or if the Play Store was just being flooded with more malicious apps.
To elaborate on this, Ahn explains the improvement in sophistication of the San Francisco developer‘s security strategy: “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.”
So, what gave Google the extra edge in 2017 to do this? Simple — sharp use of AI. “This was possible through significant improvements in our ability to detect abuse – such as impersonation, inappropriate content, or malware,” Ahn elaborates, “through new machine learning models and techniques.”
Pick Your Poison
As Ahn mentioned, three types of apps that Google cracked down on were copycats, inappropriate content, and potentially harmful applications (PHA). The first category, copycat apps, try to ride on the name brand recognition of popular apps by, you guessed it, impersonating them. Google removed more than a quarter million of these types of apps in 2017.
While copycats are usually easy to identify at face value, the next category, inappropriate content, strongly benefited from a good dose of machine learning. “We don’t allow apps that contain or promote inappropriate content, such as pornography, extreme violence, hate, and illegal activities,” Ahn says. “The improved machine learning models sift through massive amounts of incoming app submissions and flag them for potential violations, aiding the human reviewers in effectively detecting and enforcing on the problematic apps.” This resulted in the removal of “tens of thousands of apps” fitting this category.
The last category of apps that Google cut down is perhaps the sneakiest and most volatile. As with the other two, PHAs does exactly what its name implies: “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,” Ahn explains. He goes on to discuss that developers behind these apps usually “go the extra mile to make their app look as legitimate as possible.” Unfortunately for them, Google also goes the extra mile. Ahn announced that annual PHA install rates had been decreasing by 50 percent year-over-year on the Android app store.
A Safer Play Store
Last year, Google announced Google Play Protect, its security system for Android that automatically scans newly installed apps for malware. This and Google’s advanced machine learning tactics seem to be paving the way towards a safe future for Android app users. Cybersecurity is no joke, and being too safe is never possible. It’s great to see Google’s initiative.Tags: AI, AI App Developer, AI App Development, Android, android app developers san francisco, android app development, cybersecurity, cybersecurity threat, Google, google apps, google play, google play app store, google play store, google play vs itunes, san francisco AI app developer, San Francisco app developers, San Francisco iOS app development