In plain words: Instead of cameras, this system reads how a person distorts Wi-Fi signals and turns those patterns into a signature for recognizing them again later. In tests it performed about as well as the best existing methods.
Abstract
Person Re-Identification is a key and challenging task in video surveillance. While traditional methods rely on visual data, issues like poor lighting, occlusion, and suboptimal angles often hinder performance. To address these challenges, we introduce WhoFi, a novel pipeline that utilizes Wi-Fi signals for person re-identification. Biometric features are extracted from Channel State Information (CSI) and processed through a modular Deep Neural Network (DNN) featuring a Transformer-based encoder. The network is trained using an in-batch negative loss function to learn robust and generalizable biometric signatures. Experiments on the NTU-Fi dataset show that our approach achieves competitive results compared to state-of-the-art methods, confirming its effectiveness in identifying individuals via Wi-Fi signals.
Danilo Avola, Emad Emam, Dario Montagnini, Daniele Pannone, Amedeo Ranaldi
arXiv:2507.12869 · cs.CV, cs.LG · submitted Jul 17, 2025 · updated Aug 4, 2025
abstract · pdf · html
"How Wi-Fi sensing became usable tech" (2024), https://www.technologyreview.com/2024/02/27/1088154/wifi-sen...
2021 privacy comments on Wi-Fi 7 standards work for IEEE 802.11bf, https://arxiv.org/pdf/2103.14918.pdf> it has been shown that SENS-based classifiers can infer privacy-critical information such as keyboard typing, gesture recognition and activity tracking ... since Wi-Fi signals can penetrate hard objects and can be used without the presence of light, end-users may not even realize they are being tracked ... individuals should be provided the opportunity to opt out of SENS services – in other words, to avoid being monitored and tracked by the Wi-Fi devices around them. This would require the widespread introduction of reliable SENS algorithm for human or animal identification.
Would this require a worldwide database of biometric signatures for each human that opts out?