A hot potato: As Wi-Fi spreads everywhere, a new technology could identify you just by how your body disturbs wireless signals – no cameras, no devices needed. This breakthrough raises urgent questions about privacy in a world where invisible tracking might soon become routine.
Researchers at La Sapienza University of Rome have developed a method they say can re-identify individuals based solely on how their bodies disrupt Wi-Fi signals – a breakthrough likely to reignite debates over privacy and surveillance. The technique is more powerful and less invasive than biometric systems that rely on faces, fingerprints, or mobile devices, and unlike fixed-location cameras or scanners, it can track individuals across any space covered by a Wi-Fi network.
Computer scientists Danilo Avola, Daniele Pannone, Dario Montagnini, and Emad Emam, who authored the study, describe WhoFi as a novel biometric identifier. Rather than relying on visuals, wearables, or behavioral cues, it derives a person's unique "signature" from variations in Wi-Fi channel state information, which captures changes in signal amplitude and phase as electromagnetic waves interact with physical obstructions.
"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 write. "These alterations … contain rich biometric information."
To test their hypothesis, the researchers trained a deep neural network to recognize signal alterations as unique to individual bodies. The system learns to distinguish people by analyzing how each person modifies a Wi-Fi signal, even across different environments. When tested on the NTU-Fi dataset – a widely used benchmark for Wi-Fi-based human sensing – WhoFi achieved up to 95.5 percent re-identification accuracy using a transformer-based deep learning model.
This kind of human sensing using Wi-Fi is not new. Over the past decade, researchers have explored applications ranging from fall detection to through-wall presence sensing and gesture recognition. A similar approach, EyeFi, proposed in 2020, reported person re-identification accuracy of about 75 percent. The authors of WhoFi argue that their method delivers higher precision and works reliably across different locations.
Although promising from a technical perspective, Wi-Fi-based re-identification raises significant ethical concerns. Unlike cameras or RFID tags, which are visible and identifiable, Wi-Fi signals are pervasive and typically go unnoticed, as they are designed for data transmission rather than tracking. The Register notes that proponents of this emerging field describe Wi-Fi sensing as a more privacy-conscious alternative to visual surveillance because it does not capture imagery. However, critics argue that persistent tracking – especially when it occurs without a subject's knowledge or consent – could open the door to new forms of covert surveillance.
The team acknowledges the tension between innovation and privacy. While they maintain that WhoFi does not directly capture a person's identity or personal data, they also recognize the potential for misuse if deployed without proper safeguards.
For now, the research remains academic, with no planned commercial or government applications. However, as Wi-Fi-equipped environments become increasingly common, the possibility that our bodies could silently transmit identity – without any device in hand – may soon shift from experiment to everyday reality.