Professor Thorsten Strufe from KASTEL, KIT's Institute of Information Security and Dependability, explains that ordinary Wi‑Fi signals can be used to create an image of surroundings and people without cameras or a personal device. By observing radio‑wave propagation, the system behaves like a camera, but radio waves replace light waves.\n\nThe technique uses standard Wi‑Fi routers; no special hardware is required. It relies on beamforming feedback information (BFI) that is transmitted unencrypted by connected devices.

Anyone within range can capture this data and, using machine‑learning models, generate multi‑view images that reveal a person's identity.\n\nIn a study with 197 participants, the system achieved nearly 100% accuracy regardless of perspective or walking style. Strufe stresses that while the technology is powerful, it poses severe privacy risks, especially in authoritarian settings where it could monitor protests without visible cameras.\n\nResearchers call for privacy safeguards in the upcoming IEEE 802.11bf Wi‑Fi standard and urge that protections be built into future Wi‑Fi technology before exploitation scales. The project was funded by the Helmholtz Engineering Secure Systems program, and results were presented at the ACM Conference on Computer and Communications Security (CCS) in Taipei.