Project Info
Smartphone Theft Detection using Behavior Biometrics
Dejun Yang | djyang@mines.edu
Almost 75% of all Americans now own a smartphone, and that number keeps climbing. Their uniqueness and value, combined with their small size, makes smartphones ideal targets for thieves. According to Consumer Reports’ annual State of the Net Survey, there were 3.1 million smartphones stolen in 2013. To combat this, we plan to develop a theft prevention app based on users’ behavior biometrics, including smartphone pick-up and gait, to alert users on the spot.
More Information
S. Chang, T. Lu and H. Song, “SmartDog: Real-Time Detection of Smartphone Theft,” 2016 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), Chengdu, 2016, pp. 223-228.
Grand Engineering Challenge: Secure cyberspace
Student Preparation
Qualifications
Self-motivated. Good programming skills. Know or be willing to learn how to apply machine learning techniques.
Time Commitment
20-30 hours/month
Skills/Techniques Gained
Usage of APIs to access the embedded sensors in a smartphone
Machine learning techniques
How to conduct research experiments
Mentoring Plan
1. Monthly or weekly meeting
2. Beside me, I will assign a grad student as a mentor as well.