The software 'SilentSense', developed by Cheng Bo and his colleagues at the Illinois Institute of Technology, has demonstrated 99 percent accuracy in tests.
It uses the phone's built-in sensors to record the unique patterns of pressure, duration and fingertip size and position each user exhibits when interacting with their phone or tablet.
Machine learning algorithms then turn this into a signature that identifies the user - and will lock out anyone whose usage patterns do not match.
The system's accuracy can be further enhanced, by enabling the smartphone's accelerometer and gyroscope to measure how much the screen moves when you are jabbing at it.
They can also pick up on your unique gait as you walk while using the screen. In tests, 100 users were told to use the smartphone's touch screen as they would normally.
SilentSense was able to identify the phone's owner with 99 percent accuracy after no more than 10 taps. Even with an average of 2.3 touches the system was able to verify the user 98 percent of the time.
The software stops checking the user's identity when apps like games are being used. However, to maintain security, it automatically switches on when more sensitive applications, such as email or SMS, are accessed.