Humans can be tracked with unique ‘fingerprint’ based on how their bodies block Wi-Fi signals
Researchers in Italy have developed a way to create a biometric identifier for people based on the way the human body interferes with Wi-Fi signal propagation.
The scientists claim this identifier, a pattern derived from Wi-Fi Channel State Information, can re-identify a person in other locations most of the time when a Wi-Fi signal can be measured. Observers could therefore track a person as they pass through signals sent by different Wi-Fi networks – even if they’re not carrying a phone.
In the past decade or so, scientists have found that Wi-Fi signals can be used for various sensing applications, such as seeing through walls, detecting falls, sensing the presence of humans, and recognizing gestures including sign language.
Following the approval of the IEEE 802.11bf specification in 2020, the Wi-Fi Alliance began promoting Wi-Fi Sensing, positioning Wi-Fi as something more than a data transit 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 preprint paper titled, “WhoFi: Deep Person Re-Identification via Wi-Fi Channel Signal Encoding.”
(The authors presumably didn’t bother checking whether the WhoFi name was taken. But an Oklahoma-based provider of online community spaces shares the same name.)
Who are you, really?
Re-identification, the researchers explain, is a common challenge in video surveillance. It’s not always clear when a subject captured on video is the same person recorded at another time and/or place.
Re-identification doesn’t necessarily reveal a person’s identity. Instead, it is just an assertion that the same surveilled subject appears in different settings. In video surveillance, this might be done by matching the subject’s clothes or other distinct features in different recordings. But that’s not always possible.
The Sapienza computer scientists say Wi-Fi signals offer superior surveillance potential compared to cameras because they’re not affected by light conditions, can penetrate walls and other obstacles, and they’re more privacy-preserving than visual images.
“The core insight 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 state in their paper. “These alterations, captured in the form of Channel State Information (CSI), 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 results in person-specific distortions. When processed by a deep neural network, the result is a unique data signature.
Researchers proposed a similar technique, dubbed EyeFi, in 2020, and asserted it was accurate about 75 percent of the time.
The Rome-based researchers who proposed WhoFi claim their technique makes accurate matches on the public NTU-Fi dataset up to 95.5 percent of the time when the deep neural network uses the transformer encoding architecture.
“The encouraging results achieved confirm the viability of Wi-Fi signals as a robust and privacy-preserving biometric modality, and position this study as a meaningful step forward in the development of signal-based Re-ID systems,” the authors say. ®
READ MORE HERE