Researchers in Italy have developed a way to create a biometric identifier for individuals based on the way the human body interferes with the propagation of a Wi-Fi signal.
Scientists claim that this identifier, a pattern derived from the state information of a Wi-Fi channel, can re-identify a person in other locations most of the time. Observers could thus track a person as they pass through signals sent by different Wi-Fi networks – even if they don’t have a phone.
Over the past decade or so, scientists have found that Wi-Fi signals can be used for various sensing applications, such as viewing through walls, fall detection, human presence detection and gesture recognition.
Following the approval of the 802.11bf standard in 2020, the Wi-Fi Alliance began promoting Wi-Fi Sensing, positioning Wi-Fi as more than just a data transfer mechanism.
The researchers – Danilo Avola, Daniele Pannone, Dario Montagnini and Emad Emam, from La Sapienza University of Rome – call their approach “WhoFi”, as described in a pre-publication titled “WhoFi: Person Re-Identification via Wi-Fi Channel Signal Encoding” or “WhoFi: Deep Person Re-Identification via Wi-Fi Channel Signal Encoding. "
Reidentification does not necessarily reveal a person's identity. Rather, it is simply an assertion that the same person being monitored appears in different contexts. In a video, this can be done by matching the person's clothing or other distinctive features in different scenes.
Sapienza scientists report that Wi-Fi signals offer superior surveillance capabilities compared to cameras because they are not affected by lighting conditions, can penetrate walls and other obstacles, and are more privacy-protective compared to images.
“The key finding is that as a Wi-Fi signal propagates through an environment, its waveform is altered by the presence and physical characteristics of objects and people along its path,” the authors write in their study. “These changes, recorded in the form of Channel Status Information (CSI by Channel State Information), contain rich biometric information”.
CSI in the context of Wi-Fi devices refers to information about the amplitude and phase of electromagnetic transmissions. These measurements, the researchers say, interact with the human body in a way that leads to distortions that “point” to specific individuals. When processed by a neural network, the result is a unique data signature.
The researchers from Rome claim that their technique makes accurate matches to the public NTU-Fi dataset up to 95,5% of the time.
"The encouraging results achieved confirm the viability of Wi-Fi signals as a powerful privacy-protecting biometric method and point to this study as an important step forward in the development of signal-based Re-ID systems."
DOI: https://doi.org/10.48550/arXiv.2507.12869
Although the press releases will range from very select to rare, I said I'd pass...because sometimes the editors hide.
