Researchers at Karlsruhe Institute of Technology used machine learning with beamforming feedback information (BFI) to identify individuals at 99.5% accuracy. BFI requires connected devices to send constant feedback so routers can focus signals, and real-world distortions from pets, walls, and people create a mismatch between expected and received signals. That mismatch enabled extrapolation of physical characteristics and identification of 161 participants from BFI data. Even with gait changes or carrying backpacks and crates, accuracy remained 50–60%. The feedback data is unencrypted and can be accessed without directly connecting to the router.
"The study, flagged by Gizmodo, used machine learning systems to identify individuals with an accuracy rate of 99.5 percent. To do so, the researchers exploited a vulnerability in a process known as beamforming feedback information (BFI), which was introduced to allow routers to focus Wi-Fi signals on connected devices, as opposed to the older approach, which is to blanket an entire area in coverage."
Read at Futurism
Unable to calculate read time
Collection
[
|
...
]