Swedish FOI unveils WiFireNet AI that detects concealed handguns via Wi‑Fi signals
Swedish Defense Research Agency (FOI) researchers announced WiFireNet, an AI that uses Wi‑Fi channel state information to spot concealed handguns. The system combines a Wi‑Fi transmitter, a receiver, and a deep‑learning model trained on the WiFire Dataset, which pairs RGB video with reflected Wi‑Fi signals of objects such as phones, plastic and metal handguns, and water bottles.
Key points
- WiFireNet detects concealed handguns using Wi‑Fi channel state information, trained on the WiFire Dataset.
- Controlled indoor trials (up to four moving people) showed 72.5% detection precision, dropping to 53.8% for exact localization.
- System is open‑source; future work will use Wi‑Fi 7/8, but current performance struggles in unfamiliar layouts.
In controlled indoor tests with up to four moving individuals, WiFireNet achieved an average detection precision of 72.5 %. When the task required pinpointing the exact weapon location, precision fell to 53.8 %. The model also struggled in unfamiliar room layouts. The prototype used a modified IEEE 802.11a (1999) link; future versions will target Wi‑Fi 7 and Wi‑Fi 8 for higher‑resolution CSI. All code, trained weights, and the dataset have been released openly to encourage further research. Critics note that the technology’s ubiquity and the lack of regulatory frameworks raise privacy concerns.
Researchers train AI to detect concealed handguns using Wi-Fi signals
Tom's Hardware · 18 October 2026
Loading the full article…
This text was published by Tom's Hardware and written by Etiido Uko. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- Study finds Google Gemini 2.5 Flash Image complies with requests to make faces look gay · 1 src
- Anthropic says Claude traced NIST ECDSA curve seeds to 1990s C library RNG · 3 src
- What Are Native Audio Models? How Speech-to-Speech AI Skips Transcription · 1 src
- Decomp.dev shuts public index and leaderboard amid AI misuse · 2 src
- Gen-Verse releases DiscoveryRSI-27B for scientific hypothesis generation · 1 src
Comments
via GitHub Discussions