Nav: Home

Mobile app behavior often appears at odds with privacy policies

November 15, 2016

PITTSBURGH--How a mobile app says it will collect or share a user's personal information with third parties often appears to be inconsistent with how the app actually behaves, a new automated analysis system developed by Carnegie Mellon University has revealed.

An analysis of almost 18,000 popular free apps from the Google Play store found almost half lacked a privacy policy, even though 71 percent of those appear to be processing personally identifiable information and would thus be required to explain how under state laws such as the California Online Privacy Protection Act (CalOPPA).

Even those apps that had policies often had inconsistencies. For instance, as many as 41 percent of these apps could be collecting location information and 17 percent could be sharing that information with third parties without stating so in their privacy policy.

"Overall, each app appears to exhibit a mean of 1.83 possible inconsistencies and that's a huge number," said Norman Sadeh, professor of computer science in CMU's Institute for Software Research. The number of discrepancies is not necessarily surprising to privacy researchers, he added, "but if you're talking to anyone else, they're likely to say 'My goodness!'"

Sebastian Zimmeck, a post-doctoral associate who designed and implemented this system with Sadeh, will present their findings Nov. 17-19 at the AAAI Fall Symposium on Privacy and Language Technologies in Arlington, Va.

A number of federal and state laws require mobile apps to have privacy policies, such as the Children's Online Privacy Protection Act (COPPA) for mobile apps directed at children that collect personally identifiable information. However, CalOPPA requires privacy policies for any mobile app that collects personally identifiable information, regardless of whether it is directed at children or adults. Delaware has a similar law. Those state laws effectively serve as a minimum privacy threshold because app publishers usually don't market state-specific apps.

Sadeh's group is collaborating with the California Office of the Attorney General to use a customized version of its system to check for compliance with CalOPPA and to assess the effectiveness of CalOPPA and "Do Not Track" legislation.

"Just because the automated system finds a possible privacy requirement inconsistency in an app does not mean that a problem necessarily exists," Sadeh emphasized.

It's possible that when the system looks for the privacy policy it fails to find it -- the system currently looks at the app store, the company's website and also scans the code of the app. It is also possible that when it analyzes the app's source code it may make mistaken assumptions about how the code handles personal information.

"That's why a human would need to validate findings by the automated system before any enforcement or corrective action took place," Sadeh said.

Nevertheless, with substantially more than a million apps already in Google Play and the number growing by the day, such a system might help developers detect problems with their apps before they are marketed and could help make spotting violators of laws a more manageable task for regulators and privacy activists.

The automated system uses natural language processing and machine learning to analyze the text of privacy policies. It then examines the app's computer code to see whether its behavior suggests it shares personal information and therefore should have a privacy policy. It also checks whether the app's data collection and sharing behavior is consistent with an existing privacy policy.

This approach is far faster than any human review. Two years ago, for instance, 1,200 apps were reviewed in a week's time by the joint efforts of 26 international privacy enforcement agencies. The Carnegie Mellon system, by comparison, was able to review almost 18,000 in about 31 hours, or about 6 seconds per app.

"With a few servers, we should be able to scan all the free apps in the Google Play store every month," Sadeh said.

It would still require a lot of manpower to systematically review those apps flagged by the automated system, however. Instead, the system could be used to assign scores to apps and help regulators focus on the seemingly most egregious ones. This could result in letters or emails being sent to developers asking for clarification.

"Some discrepancies are to be expected because not all developers are sophisticated about privacy," Sadeh said.

For instance, one common error is to build an app that uses Google Maps, but fail to mention the processing of location information in the related privacy policy.

"Whenever you're using Google Maps," he noted, "you're effectively sharing personal information with Google."
-end-
The National Science Foundation, the Defense Advanced Research Projects Agency and the Air Force Research Laboratory supported this work. In addition to Sadeh, the researchers included Sebastian Zimmeck, Ziqi Wang, Lieyong Zou, Florian Schaub, Shomir Wilson and Bin Liu of Carnegie Mellon's School of Computer Science, as well as Steven M. Bellovin of Columbia University, Roger Iyengar of Washington University of St. Louis and Joel Reidenberg of the Fordham University School of Law.

About Carnegie Mellon University: Carnegie Mellon is a private, internationally ranked research university with programs in areas ranging from science, technology and business, to public policy, the humanities and the arts. More than 13,000 students in the university's seven schools and colleges benefit from a small student-to-faculty ratio and an education characterized by its focus on creating and implementing solutions for real problems, interdisciplinary collaboration and innovation.

Carnegie Mellon University

Related Privacy Articles:

Kids, parents alike worried about privacy with internet-connected toys
University of Washington researchers have conducted a new study that explores the attitudes and concerns of both parents and children who play with internet-connected toys.
Study applies game theory to genomic privacy
A new study from Vanderbilt University presents an unorthodox approach to protect the privacy of genomic data, showing how optimal trade-offs between privacy risk and scientific utility can be struck as genomic data are released for research.
When artistic freedom violates somebody's privacy
It can be quite an honor to be included in a literary work -- but it may also be a demeaning experience.
Study examines effect of privacy controls on Facebook behavior
A new study from the Naveen Jindal School of Management at UT Dallas assesses the impact of Facebook's granular privacy controls and its effects on user disclosure behavior.
Mobile app behavior often appears at odds with privacy policies
How a mobile app says it will collect or share a user's personal information with third parties often appears to be inconsistent with how the app actually behaves, a new automated analysis system developed by Carnegie Mellon University has revealed.
Children's health and privacy at risk from digital marketing
For the first time, researchers and health experts have undertaken a comprehensive analysis of the concerning situation in the World Health Organisation European Region regarding digital marketing to children of foods high in fats, salt and sugars
Exploring the relationship of ethics and privacy in learning analytics and design
The Springer journal Educational Technology Research and Development has published a special issue that examines the relationship of ethics and privacy in learning analytics, guest edited by Dr.
Just give me some privacy
Not everyone who strives to navigate the internet without being tracked is up to no good.
System helps protect privacy in genomic databases
In the latest issue of the journal Cell Systems, researchers from MIT's Computer Science and Artificial Intelligence Laboratory and Indiana University at Bloomington describe a new system that permits database queries for genome-wide association studies but reduces the chances of privacy compromises to almost zero.
IU study finds despite expectations of privacy, one in four share sexts
A new study from Indiana University researchers shows that although most people who engage in sexting expect their messages to remain private, nearly one in four people are sharing the sexual messages they receive.

Related Privacy Reading:

Best Science Podcasts 2019

We have hand picked the best science podcasts for 2019. Sit back and enjoy new science podcasts updated daily from your favorite science news services and scientists.
Now Playing: TED Radio Hour

Anthropomorphic
Do animals grieve? Do they have language or consciousness? For a long time, scientists resisted the urge to look for human qualities in animals. This hour, TED speakers explore how that is changing. Guests include biological anthropologist Barbara King, dolphin researcher Denise Herzing, primatologist Frans de Waal, and ecologist Carl Safina.
Now Playing: Science for the People

#SB2 2019 Science Birthday Minisode: Mary Golda Ross
Our second annual Science Birthday is here, and this year we celebrate the wonderful Mary Golda Ross, born 9 August 1908. She died in 2008 at age 99, but left a lasting mark on the science of rocketry and space exploration as an early woman in engineering, and one of the first Native Americans in engineering. Join Rachelle and Bethany for this very special birthday minisode celebrating Mary and her achievements. Thanks to our Patreons who make this show possible! Read more about Mary G. Ross: Interview with Mary Ross on Lash Publications International, by Laurel Sheppard Meet Mary Golda...