Skip to main content

Personal Privacy Assistant uses AI to learn users’ app preferences

The Personalized Privacy Assistant Project
If you’ve been really paying attention to the world of mobile devices over the past decade, you may possibly have noticed that users have a habit of downloading apps for their phones. Apps are all well and great but they can also have a nasty habit of gathering data about their users and feeding it back to developers.

Fortunately, smartphone platform makers like Apple and Google have responded by giving users the ability to limit individual privacy settings within apps — deciding whether they want to hand over access to contact, location data, sensor information, camera access, and more. Increasingly, these can be toggled individually in a way that restores sovereignty to the user over their system.

Good, right? Well, kind of.

“The number of settings that we have to control has truly become overwhelming and unrealistic,” Norman Sadeh, a professor at Carnegie Mellon’s School of Computer Science, told Digital Trends. “A typical user will have 50 or more apps on his or her cellphone. Conservatively these apps may have controls for three different permissions. If you have to decide which of these permissions you’re willing to grant, that means that the average user has to configure 150 different permissions. Very, very few people are willing to do that.”

Along with colleagues, Sadeh is working on a solution in the form of the so-called Personal Privacy Assistant Project — an app designed to make privacy decisions more manageable.

“Different users will be happy with different permissions, but previous research has shown that you can predict an individual’s preferences by asking them a small number of questions,” he said. “Using AI and machine learning technology, we’ve been able to build a privacy assistant able to look at the apps you’ve got on your cellphone, ask a few questions, and make recommendations about how you may want to configure your settings.”

In a pilot study, users accepted almost 80 percent of the recommendations made by the privacy assistant — making this a potentially transformative way to deal with an important issue, without surrendering all of your free time to reading pages of terms and conditions.

An Android version of Personal Privacy Assistant is planned for release over the next few weeks, designed for rooted (that’s “jailbreaking” for the iOS community) users. Sadeh also said he hopes some of the big players in the mobile space may consider incorporated similar tools in future releases.

As the world moves toward body data-tracking wearable devices and smart homes, this topic will only become more critical.

Editors' Recommendations

Luke Dormehl
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
Deep-learning A.I. is helping archaeologists translate ancient tablets
DeepScribe project 1

Deep-learning artificial intelligence is helping grapple with plenty of problems in the modern world. But it also has its part to play in helping solve some ancient problems as well -- such as assisting in the translation of 2,500-year-old clay tablet documents from Persia's Achaemenid Empire.

These tablets, which were discovered in modern-day Iran in 1933, have been studied by scholars for decades. However, they’ve found the translation process for the tablets -- which number in the tens of thousands -- to be laborious and prone to errors. A.I. technology can help.

Read more
This A.I.-powered app can spot skin cancer with 95 percent accuracy
skinvision app detects cancer 95 percent  38

Detect skin cancer with your phone using SkinVision

If you’re going to trust your smartphone to do something as important as detect the most common forms of skin cancer, you want to be pretty darn sure that it works as advertised. Fortunately, the claims of an app called SkinVision appear to be accurate.

Read more
5 ways that future A.I. assistants will take voice tech to the next level
amazon alexa laugh echo night creepy feature

Since Siri debuted on the iPhone 4s back in 2011, voice assistants have gone from unworkable gimmick to the basis for smart speaker technology found in one in six American homes.

“Before Siri, when I talked about [what I do] there were blank stares,” Tom Hebner, head of innovation at Nuance Communications, which develops cutting edge A.I. voice technology, told Digital Trends. “People would say, ‘Do you build those horrible phone systems? I hate you.’ That was one group of people’s only interaction with voice technology.”

Read more