What Is EarSpy Attack?
The point worth mentioning here is that EarSpy is an academic effort of researchers from five American universities including:
Texas A&M University New Jersey Institute of Technology Temple University University of Dayton Rutgers University
This type of attack has been explored in smartphone loudspeakers. If we talk about the ear speakers, they were considered too weak to generate enough vibration for eavesdropping risk in order to turn such a side-channel attack into a practical one. However, modern handsets use more powerful stereo speakers as compared to old models which produce much better sound quality and stronger vibrations. No doubt, modern phones use more sensitive motion sensors and gyroscopes that have the ability to record even the tiniest resonances from speakers. In the experiments, the researchers used a OnePlus 7T and OnePlus 9 along with varying sets of pre-recorded audio that was played only through the ear speakers of the two gadgets. Furthermore, the team also used the third-party app ‘Physics Toolbox Sensor Suite’ in order to capture accelerometer data during a call and then feeds it to MATLAB for analysis in order to extract features from the audio stream. A machine learning (ML) algorithm is said to be trained using readily available datasets in order to recognize speech content, caller identity, and gender. Also Read: Google To Pay $29.5 Million To Settle Lawsuits Over User Location Tracking – PhoneWorld
