US Edition
WhoFi: Unique 'fingerprint' based on Wi-Fi interactions
ROME, ITALY, JUL 22 – WhoFi uses Wi-Fi signal distortions to create biometric fingerprints with up to 95.5% accuracy, enabling device-free tracking and raising new privacy concerns.
- Recently, researchers at La Sapienza University of Rome introduced WhoFi, which identifies individuals by body-induced Wi-Fi distortions.
- Previous trials in 2020 achieved only 75% accuracy in earlier experiments, limiting their usefulness for true surveillance.
- According to the La Sapienza University research paper, up to 95.5% re-identification accuracy is achieved, complemented by analysis of subtle distortions in Wi-Fi Channel State Information .
- Critics warn that persistent tracking could open the door to new forms of covert surveillance, raising significant privacy concerns, critics argue, and implications for individual rights.
- Soon, the approach may shift to everyday reality in Wi-Fi-equipped environments, as the lab works to turn theory into practical solutions.
15 Articles
15 Articles
WhoFi is a new technology that has the ability to track people via WiFi. It is more accurate and detects where each person is located as if it were a radar.
Have you ever left your phone at home because you were afraid of being watched? You'd rather leave yourself at home.
The system, called “WhoFi”, was created by researchers from the University of La Sapienza in Rome. The method is based on how the human body interferes with the spread of the Wi-Fi signal. The method works even if the person no longer carries any electronic device. Today's technology no longer keeps pace with what we live today. What appears to be a scientific reality at some time in the SF is now. This is because a team of Italian researchers h…
AI-Driven Wi-Fi Biometrics WhoFi Tracks Humans Behind Walls with 95.5% Accuracy
Researchers have introduced WhoFi, an AI-powered deep learning pipeline that leverages Wi-Fi Channel State Information (CSI) for person re-identification (Re-ID), achieving a remarkable 95.5% Rank-1 accuracy on the NTU-Fi dataset. Traditional visual Re-ID systems, reliant on convolutional neural networks (CNNs) and features like color histograms or Histograms of Oriented Gradients (HOG), falter under occlusions, varying […] The post AI-Driven Wi…
Coverage Details
Bias Distribution
- 75% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
