A new method of attacking biometric security: Fingerprints can be recreated from sounds

A group of researchers from China and the United States has presented a new method of attacking the automatic fingerprint identification system (AFIS). According to their research, by using the sound characteristics generated by swiping a finger across a touchscreen, attackers can successfully recreate partial fingerprints.

The innovative attack, known as PrintListener, uses algorithms to process audio signals to recreate a fingerprint template. After numerous experiments, the researchers claim to have successfully attacked up to 27.9% of partial fingerprints and 9.3% of full fingerprints.

Attackers on the Internet are highly likely to pick up the sounds of friction. The source of finger swipe sounds can be such popular applications as Discord, Skype, WeChat, FaceTime, etc. Any communication application in which users carelessly swipe the screen while the device's microphone is active.

Source: Tom's Hardware