Search This Blog

Powered by Blogger.

Blog Archive

Labels

Showing posts with label speech recognition. Show all posts

Hackers may soon able to decode what you are typing on your device






The technology advancement in smartphones may soon enable hackers to intercept what the user is typing on their devices by analyzing the sound of the keypad.

The researchers at Cambridge University and Sweden’s Linkoping University were able to extract passwords by deciphering the sound waves generated by fingers tapping on smartphone’s touch screens.

‘When a user enters text on the device’s touchscreen, the taps generate a sound wave. The device’s microphones can recover the tap and correlate it with the keystroke entered by a victim.’

According to the study, using a spying app, a malicious actor can decode what a person is typing. The study was first reported by the Wall Street Journal. “We showed that the attack can successfully recover PIN codes, individual letters, and whole words,” the researchers wrote.


‘The spying app may have been installed by the victim herself, or by someone else, or perhaps the attacker gave the device to the victim with the app pre-installed – there are several companies offering such services, such as mSpy. We also assume the app has microphone access. Many apps ask for this permission and most of us blindly accept the list of demanded permissions anyway.’

The researchers programmed a machine-learning algorithm that could detect and analyze the soundwave for specific keystrokes. On Smartphone, the researchers were able to correctly replicate the passwords seven times out of 27, within 10 attempts. While on tablets, they achieved better results, replicating for password 19 times out of 27 within 10 attempts.

“We found the device’s microphone(s) can recover this wave and ‘hear’ the finger’s touch, and the wave’s distortions are characteristic of the tap’s location on the screen,” the researchers wrote. “Hence, by recording audio through the built-in microphone(s), a malicious app can infer text as the user enters it on their device.”