Researchers from the Karlsruhe Institute of Technology (KIT) have demonstrated that it is now possible to identify a person using only Wi-Fi signals in the environment. Unlike traditional identification methods, this approach does not require the person to have a smartphone or tablet connected to the network. It is enough to have working routers or other Wi-Fi transmitters nearby that communicate with each other. Interesting Engineering writes about this.
According to the study, the new Wi-Fi technology analyzes the interaction of radio waves between standard Wi-Fi devices and creates a highly detailed image of a person's presence, posture, and movements, similar to a camera image, but formed solely from radio signals.
Professor Torsten Strufe from the Institute for Information Security and Reliability (KASTEL) explained that radio waves can reproduce images of people and space, similar to how a camera works with light. He emphasized that the system is able to detect a person even in the absence of their own device, using active Wi-Fi networks nearby. This means that a person’s presence and movements can be recorded without their knowledge.
Another researcher at KASTEL, Julian Todt, warned that any Wi-Fi router could potentially become a surveillance tool. For example, if a person regularly walks past a cafe with an active network, their movements could be recorded and used by government agencies or companies.
Strufe added that while there are simpler methods of surveillance, such as video surveillance cameras, the mass spread of Wi-Fi poses the risk of forming an almost comprehensive surveillance infrastructure.
Unlike previous approaches that used LIDAR sensors or channel state information (CSI), which describes in detail how a radio signal travels from transmitter to receiver, the new technique uses only standard Wi-Fi devices and does not require specialized equipment. It is based on the analysis of beamforming feedback (BFI) signals, which are transmitted in an unencrypted form. This data allows the creation of images of objects from different angles, which are then processed by machine learning algorithms.
According to experts, AI models trained with this recognition method will be able to identify a person in just a few seconds.
It is noted that in a recognition experiment conducted with the participation of 197 people, the researchers achieved almost 100% accuracy in identifying a person regardless of their walking style or direction of gaze. This indicates significant risks to privacy, because this method can recognize a person quite quickly, imperceptibly and without complex equipment.