In recent research, mobile phone calls are tracked remotely using sensors

In recent research, mobile phone calls are tracked remotely using sensors ...

Researchers have developed a technique to detect the vibrations of a mobile phone''s earpiece and decipher what the person on the other side of the call was saying with up to 88% accuracy. The team at Pennsylvania State University used an off-the-shelf automotive radar sensor and a novel processing technique to uncover this significant security concern.

"As technology becomes more reliable and robust over time, adversaries will be susceptible to misuse of such sensing technologies," says Penn State''s attorney general.

"Our demonstration of this type of exploitation contributes to the pool of scientific literature that general states, "Hey! Automotive radars can be used to eavesdrop audio. "We must do something about this," Basak said.

The radar is operating in the millimetre-wave (mmWave) spectrum, particularly in the bands of 60 to 64GHz and 77 to 81GHz, which prompted the researchers to name their approach "mmSpy." This is a subset of the radio spectrum used for 5G, the fifth-generation standard for communication systems across the globe.

The researchers recreated people speaking through the headphones of a smartphone in the mmSpy tutorial described in the IEEE Symposium on Security and Privacy (SP) in 2022.

The earpiece of the phone vibrates from the speech, and the vibration extends across the phone.

  • Meta Unveils ''''Make-A-Video'''' AI Text-To-Video Generator: Details

"We use the radar to sense this vibration and reconstruct what was said by the person on the other side of the line," said Basak.

According to the researchers, Mahanth Gowda, an assistant professor at Penn State, the method works even if the audio is completely inaudible to both humans and microphones nearby.

"This isn''t the first time similar vulnerabilities or attack techniques have been discovered,," Basak said. This particular feature detecting and reconstructing speech from the other side of a smartphone line has not been explored.

The researchers then feed that to machine learning courses taught to classify speech and reconstruct audio.

According to the experts, when the radar detects vibrations from a foot away, the processed speech is 88% accuracy. That''s down to 48% accuracy at six feet, as the radar moves from the phone.

Basak said the researchers can then choose, modify, or classify words as needed once the speech is rebuilt.

The team is continuing to refine their approach in order to better understand non only how to protect against this security vulnerability, but also how to exploit it for the benefit.

"The approach that we used can be used in industrial equipment, smart home systems, and building-monitoring systems," Basak said.

According to the researchers, similar home maintenance or health monitoring procedures may benefit from this type of monitoring.

"Imagine a radar that might monitor a user and solicit help if a health parameter changes in a dangerous way," Basak said.

"When problems and issues are identified, radars in smart homes and industries can enable a quicker turnaround, according to the right set of target actions.