The good news is that the malware was part of a research experiment by white hats, and poses no threat to smartphone users at the time.
Researchers from five universities in the US — Texas A&M University, New Jersey Institute of Technology, Temple University, University of Dayton, and Rutgers University — have collaborated and built EarSpy.
EarSpy, a side channel attack, exploits the fact smartphones’ speakers, motion sensors, gyroscopes and gyroscopes are all better over the years.
The malware attempts reading data from motion sensors. It can also echo during conversations. This was not an attack vector in previous years because the amplifiers were not as powerful.
The researchers used two smartphones to prove their point: one from 2016 and one in 2019. The difference in data collection was very evident.
The researchers tested whether the data could be used to identify the gender of a caller or recognize speech using the OnePlus 7T, and OnePlus 9.
Previously, caller gender identification ranged between 77.7% to 98.7%. Caller ID was between 63.0%-91.2%. Speech recognition dance between 51.8% – 56.4%
“Because there was ten different categories, the accuracy still showed five-times greater accuracy than a random guess which means that the vibration caused the accelerometer data by the earpiece caused some characteristic effect,” the researchers explained in a white paper.
On the OnePlus 9 smartphone, the researchers were able to guess the gender of the caller (88.7% average), but identification dropped below 73.6% average. Speech recognition declined between 33.3% to 41.6%.
Through: Computer(Opens in new tab)
[Denial of responsibility! reporterbyte.com is an automatic aggregator of the all world’s media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, all materials to their authors. If you are the owner of the content and do not want us to publish your materials, please contact us by email – reporterbyte.com The content will be deleted within 24 hours.]