A group of students lead by Romit Roy Choudhury,Builded a mobile application that is able to figure out the each and every movements of a smartwatch to recognize the keys pressed by the user On Keyboard. The researchers planning to present it this week at the MobiCon 2015.
This project is called Motion Leaks (MoLe) is funded by the National Science Foundation, the researchers have installed the application on a Samsung Gear Live smartwatch to test the application.No additional tool, software and hardware is required to track the movement of user on keyboard.The watch’s built-in motion sensors like accelerometer and gyroscope were able to create a 3D map of the user’s hand movements while typing on a keyboard.
“The app uses an accelerometer and gyroscope to track the micro-motion of keystrokes as a wearer types on a keyboard. After collecting the sensor data, researchers ran it through a “Keystroke Detection” module, which analyzed the timing of each keystroke and the net 2-D displacement of the watch. For example, the left wrist moves farther to type a “T” than an “F.” You can see how it works in the researchers’ video.” states the blog post published by the researchers,
Further, the Researchers group created two algorithms for analyzing what keys were actually pressed and for guessing the words typed by the user.
The two algorithms are used in conjunction
The first algorithms allows the researchers to detect when the user starts to type on a keyboard and create a map where the user would pressed the key on keyboard.
The second algorithm receives the data from first algorithms and analyzing the pauses between smartwatch (left hand) keystrokes, it is able to detect how many letters were pressed with the right hand.
The algorithm uses a simple dictionary lookup to discover the words typed on the keyboard.
Currently, MoLe can’t sight special characters (numbers, punctuation, and symbols), the space bar key still poses some difficulties.
The application developed for the MoLe project solely works on a Samsung Gear Live smartwatch however researchers say that, a similar app can be developed for alternative smartwatch models.
It is easy to exploit every IoT device,mainly wearable device to spy on user.On May 2015, researchers at Context Information Security have demonstrated that it is very easy to monitor IoT devices that implement the Bluetooth Low Energy protocol.
