Swedish FOI researchers train WiFireNet to spot concealed handguns via Wi-Fi
AI researchers at the Swedish Defense Research Agency (FOI) have developed WiFireNet, a system that identifies concealed handguns by analyzing channel state information from how objects distort ambient Wi-Fi signals, pitched as a non-intrusive alternative to visible cameras and metal detectors. The team built the WiFire Dataset by simultaneously recording RGB video and reflected Wi-Fi signals of people carrying objects, and trained a deep learning model on items including a plastic handgun, a metal water bottle, a real metal handgun and a phone. In controlled indoor trials tracking up to four moving people, the system averaged 72.5% handgun-detection precision, falling to 53.8% when required to pinpoint the weapon's location on the carrier, and it performs worse in unfamiliar layouts. The prototype used a modified 1999 IEEE 802.11a implementation, with Wi-Fi 7 and Wi-Fi 8 planned for later phases; the researchers open-sourced the code, models and dataset.
The report notes that Wi-Fi sensing is gaining traction as a surveillance technology requiring little equipment, while critics argue its ubiquity and the lack of regulatory frameworks raise serious privacy concerns.
A group of AI researchers at the Swedish Defense Research Agency (FOI) has developed an AI system that can identify concealed handguns using Wi-Fi signals, offering a non-intrusive alternative to visible cameras and cumbersome metal detectors. Detailed in a paper posted on arXivWi-Fi on October 13, the system, called WiFireNet, analyzes channel state information from how an object distorts ambient Wi-Fi signals. The full system comprises a Wi-Fi transmitter, a Wi-Fi receiver, and the WiFireNet AI.
When ordinary Wi-Fi signals encounter an object in their path, they penetrate and bounce off in ways specific to that object, based on its shape, orientation, and material. This data, the channel state information, can be analyzed to identify the object with high accuracy. Security researchers previously disclosed a technique that lets ordinary Wi-Fi routers identify people with 99.5% accuracy.
To build the WiFireNet system, the researchers first created a dataset, dubbed the WiFire Dataset, by simultaneously recording RGB footage and the reflected Wi-Fi signals of people walking around with objects ranging from phones to handguns. The researchers then trained a deep learning model on the massive dataset, using video clips to match the visuals of a concealed handgun with its specific Wi-Fi signature, or channel state information. To ensure the system could specifically distinguish a handgun from everyday items of similar shape or material, the researchers trained it on recordings of a plastic handgun, a metal water bottle, a real metal handgun, and a phone.
#WiFireNet#Swedish Defense Research Agency (FOI)#WiFire Dataset#arXiv