A PLATFORM FOR CONTEXTUAL MOBILE PRIVACY

Abstract

We developed a system that balances the privacy needs of users and organizations when using personal devices in the workplace-- "Bring Your Own Device" (BYOD) environments. In so doing, we performed qualitative interviews with extreme users, to under- stand their privacy needs, the shortcomings of current systems, and their existing coping mechanisms. Based on these interviews, we developed a system that applies machine-learning to automatically infer when access to sensitive data is likely to be expected by the user. We performed a field study to collect real-world training data to train the classifier offline. In parallel, we performed an online study to evaluate designs for a user interface (i.e., a "privacy management dashboard"). Based on our study results, we implemented our designs into the Android platform and performed a subsequent field study to validate our designs.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 2017
Accession Number
AD1044904

Entities

People

  • Nathan Good
  • Serge Egelman

Organizations

  • International Computer Science Institute

Tags

Communities of Interest

  • Cyber
  • Human Systems
  • Materials and Manufacturing Processes
  • Weapons Technologies

DTIC Thesaurus Topics

  • Air Force
  • Computer Programming
  • Computer Programs
  • Computers
  • Information Science
  • Machine Learning
  • Mobile Devices
  • Mobile Operating Systems
  • Mobile Phones
  • Network Science
  • Operating Systems
  • Smartphones
  • Social Media
  • Supervised Machine Learning
  • Text Messaging
  • User Interface
  • Web Browsers

Fields of Study

  • Computer science

Readers

  • Cybersecurity.
  • Neural Network Machine Learning.
  • Software Engineering

Technology Areas

  • AI & ML