# Ordinary WiFi Can Identify People With Near-Perfect Accuracy, German Researchers Show

*2026-08-12 22:01 UTC · Technology · 1 min read*

> KIT researchers used unencrypted WiFi beamforming data to identify 197 test subjects with near-100% accuracy, no cameras or devices required.

Researchers at the Karlsruhe Institute of Technology (KIT) have shown that everyday WiFi routers can identify individual people with near-100% accuracy, without cameras, sensors, or the person carrying any connected device.

The team, led by Professor Thorsten Strufe together with Julian Todt and Felix Morsbach, exploited beamforming feedback information (BFI) — unencrypted data that WiFi devices and routers routinely exchange to optimize signal transmission. By analyzing how radio waves reflect off a person's body, machine learning models built a radio-based "image" that reliably distinguished between 197 test participants, regardless of viewing angle or how they moved.

"By observing the propagation of radio waves, we can create an image of the surroundings and of persons," said Strufe. Todt added that the finding "turns every router into a potential means for surveillance." The team presented the work, titled "BFId: Identity Inference Attacks Utilizing Beamforming Feedback Information," at the ACM Conference on Computer and Communications Security (CCS) in Taipei, and is calling for privacy safeguards to be built into the upcoming IEEE 802.11bf WiFi-sensing standard before it ships.

## Sources

- [sciencedaily.com](https://www.sciencedaily.com/releases/2026/08/260811052857.htm)

---
TechTools News · https://techtools.cz/tools/news/article/2177-ordinary-wifi-can-identify-people-with-near-perfect-accuracy-german-researchers
Česká verze: https://techtools.cz/tools/news/clanek/2250-bezna-wifi-dokaze-identifikovat-lidi-s-temer-dokonalou-presnosti-ukazuji