Swedish Researchers Develop AI That Detects Concealed Weapons Using Wi-Fi Signals
Researchers from the Swedish Defence Research Agency have developed an open-source artificial intelligence system that can detect concealed handguns by analyzing wireless signal distortion.
Researchers at the Swedish Defence Research Agency (FOI) have introduced an artificial intelligence system capable of detecting concealed handguns using Wi-Fi signals as an alternative to visible cameras and metal detectors. Detailed in a paper published on the arXiv platform on October 13, the system called WiFireNet analyzes channel state information from the distortions that objects create in ambient Wi-Fi signals.
The WiFireNet system consists of a Wi-Fi transmitter, a Wi-Fi receiver, and an artificial intelligence component. When normal Wi-Fi signals encounter an object in their path, they penetrate and reflect differently depending on the object's shape, orientation, and material. This channel state information data can be analyzed to identify the object with high accuracy. Security researchers previously described a technique allowing ordinary Wi-Fi routers to identify humans with 99.5% accuracy.