social network

Researchers have suggested how to track a smartphone with GPS off

A team of researchers from the Institute of Electrical and Electronics Engineers (IEEE) has developed a PinMe system that allows it to track its location based on open data and information from various smartphone sensors with an accuracy comparable to GPS. In this regard, researchers urge gadget manufacturers to add a software solution that disables the work of all sensors, not just GPS.




Scientists have discovered a security hole in smartphones. Comparing information from the accelerometer and gyroscope with the open data – maps and weather reports, they were able to determine the person’s location, route and mode of transport.

The PinMe application developed by researchers shows how using computer training methods and information from harmless sensors it is possible to obtain important information about human life, Pratik Mittal, associate professor of electrical engineering at Princeton University, co-author of the study. Unlike satellite navigation, information from sensors does not require permission to access.

“Hackers can convince a ship or an unmanned vehicle that they are in a place different from their real location, which can be a problem for US naval vessels navigating international waters, for example, or for the safety of autonomous car passengers,” says Nirej Jha , Professor of Princeton University and co-author of the study. According to him, the PinMe team already communicates with technology companies about licensing the application as a navigation tool.

For the experiment, scientists collected data from smartphones Galaxy S4 i9500, iPhone 6 and iPhone 6S, which were used by three people within 24 hours after installation of the PinMe application. Subjects went on foot, went by car, train, flew an airplane in Philadelphia, Dallas, Princeton and other cities.

To start, PinMe read the information about the last IP-address of the smartphone and the status of the network to determine the last connection to Wi-Fi – so the application received a starting point for further work. Then the application used an algorithm that was “trained” by machine learning to recognize the difference between walking, driving, flying and other modes of travel. For this purpose, the data from the sensors was used-the direction and speed of movement, the frequency of the stops, and altitude above sea level.

After determining the mode of movement, PinMe included a new algorithm and began to compose the user’s route. OpenStreetMaps Servicewas used to obtain the actual navigation data. Google Maps helped to determine the location by comparing it with a map of elevations above sea level. To clarify the route, the application used the Weather Channel weather service : accurate information on air temperature and pressure helps to eliminate the influence of weather conditions on the information collected by sensors. Data on the routes were compared with the schedule of airlines or railway lines.

When traveling from Philadelphia to Dallas by plane, the application first determines the mode of transport by changes in altitude and overclocking, and then – by the time zone, weather and schedule, takes the place of takeoff and landing.

In the illustration below, green and yellow marked the route, tracked with PinMe – traffic on the car and on foot, black – a GPS-built route.

These researchers did not become the first to use accelerometers to track people. In 2010, the Japanese telecommunications corporation KDDI, mobile operator au, developed an application for tracking employee movements in the company. The goal of the developers was total control over employees in order to increase the efficiency of their work. The data from the accelerometer allowed to determine the movement along a flat surface and along the stairs, the speed of movement, trips to the toilet. Moreover, the smartphone at the waist of the cleaner could determine the difference between washing the floors, sweeping and shaking out the garbage can.

In 2015, experts from the University of Nanking in China used data from the accelerometer to monitor the movement of people in the subway: “Trains in the metro are moving along rails, so their patterns of movement are different from cars and buses traveling along roads, And since there are no two identical sections connecting adjacent metro stations, patterns of movement of trains at different time intervals can also be distinguished among themselves. ” For work it is necessary to make a map of the metro, then to determine the routes with an accuracy of 70% to 92%.

The scientific work was published on February 5, 2018 on the website of the Library of Cornell University. DOI: 10.1109 / TMSCS.2017.2751462.

Back to top button