Overview

• An AI method targets unencrypted Beamforming Feedback Information exchanged between access points and client devices to infer distinctive propagation patterns.
• In lab tests with 197 participants, the system identified individuals with near‑100% accuracy using only commodity routers, laptops or IoT hardware.
• The approach can single out people who carry no devices, requires only radio‑range access to a network, and can work through walls.
• The findings were presented at the ACM Conference on Computer and Communications Security in Taipei under the title “BFId,” with authors urging encryption or restrictions in future WLAN standards such as IEEE 802.11bf.
• Industry‑wide countermeasures have not been announced, and some coverage noted the public link to the paper was temporarily inaccessible.