Forgot your password?
Close
typodupeerror
Wireless Networking

Researchers Use Ordinary WiFi Connections to Create Images of Nearby People and Their Surroundings (sciencedaily.com) 39

Posted by EditorDavid from the see-you-later dept.
Science Daily reports: Researchers showed that unencrypted signals routinely exchanged between WiFi devices and routers can be used to create radio-based images of people and recognize them within seconds. In tests involving 197 participants, the system identified individuals with nearly 100% accuracy, even from different angles and regardless of how they walked. "By observing the propagation of radio waves, we can create an image of the surroundings and of persons who are present," says Professor Thorsten Strufe from KASTEL, KIT's Institute of Information Security and Dependability. "This works similar to a normal camera, the difference being that in our case, radio waves instead of light waves are used for the recognition," explains the cybersecurity expert.

Because the technique analyzes radio waves moving through a space, a person does not need to have a phone, smartwatch, or other WiFi enabled device with them. "Thus, it does not matter whether you carry a WiFi device on you or not." Even turning off your own device would not necessarily prevent the system from working. "It's sufficient that other WiFi devices in your surroundings are active...."

Connected devices routinely send information back to the router to help optimize wireless communication. These signals, known as beamforming feedback information (BFI), are transmitted without encryption, meaning that anyone within range can potentially read them. By analyzing that information, the system can generate images of people from multiple viewpoints. Those images can then be used to determine a person's identity. Once the machine learning model has already been trained to recognize individuals, the identification process takes only a few seconds.
This discussion has been archived. No new comments can be posted.

Researchers Use Ordinary WiFi Connections to Create Images of Nearby People and Their Surroundings More

Researchers Use Ordinary WiFi Connections to Create Images of Nearby People and Their Surroundings

Comments Filter:

  • I told you (Score:5, Funny)

    by Waffle Iron ( 339739 ) on Sunday August 16, 2026 @10:53AM (#66291318)

    People thought that I was crazy for wearing this sharply angled black stealth suit.

    Who's laughing now?

  • Only one image in the story, and it is AI-generated. Let's see real images. The surveillance aspect is scary though.

    • There are no images at all in the original paper. Haven't read it yet.

    • Re: (Score:2)

      by haruchai ( 17472 )

      seems everywhere is becoming a surveillance state and gov't and big tech won't give up even if they lose some battles with rich assholes like Larry Ellison saying "citizens will be on their best behavior because we're constantly recording & reporting everything"

  • Could have sworn I've seen a Slashdot story on this a few months ago.

    • The same site ran the identical story in May of 2026. It's even linked at the bottom of TFA. Can't blame Slashdot for duping a dupe.

  • Baby steps (Score:5, Informative)

    by Smonster ( 2884001 ) on Sunday August 16, 2026 @11:01AM (#66291332)
    This technique is far from new. It’s been around for well over a decade. If there is any innovation, it’s in the algorithms that identify individuals with a better accuracy.

    • Is using BFI novel? I hadn't seen that before personally.

    • Do you mean using AI?

      - sorry, I'll see myself out.
      • There is no AI in the traditional sense, it is just marketing speak. The boosters have moved the goal post for what they think the world should call AI. What has historically thought of AI has been renamed as AGI (Artificial General Intelligence). What they are now calling AI are complicated logic based if/then scripts that work on defined sets of probability based outcomes. That isn't to say it isn't useful when used in specific ways. Those language models can turn someone who is good at something into a m

    • Are you implying these folks didn't invent RADAR?

  • a reason for running cable everywhere. Except remember way back how freeing Wi-Fi was to use with mobiles and laptops.

  • A far more newsworthy and interesting story was how they hack into pcs using the speaker

  • Tinfoil (Score:2, Funny)

    by Shakes Fist ( 10502847 )
    So, it's full bodysuit rather than just a hat now?

  • What is the difference between this and RADAR?

    The pitch seems to be that a WiFi device could do presence detection and some how use that against you. How they could use that against me has me scratching my head. But, I do feel like I should be scared. So, they've got that going for them.

    • The only difference is the frequencies used and the off-the-shelf nature of the devices.

      I think this is great. Now everyone can own a TSA grade body scanner, but one with no government oversight. After all, how is a person going to know if they've been wifi body scanned, or just close enough to use the wifi?

    • What is the difference between this and RADAR?

      In RADAR the transmitting and receiving systems are controlled by the same system. That system determines when to transmit and when to listen with time of flight giving the range and directional antennas giving rough angle to the reflection.

      In this technique, the WiFi transmitters are always transmitting and the receivers are trying to gather information from the interference caused by people obstructing the signal. Imagine having fairly powerful lights at one end of a room and a translucent sheet blockin

  • I see a new market for tinfoil hats. Or maybe tinfoil suits.

  • This is likely the proceedings with the paper:

    https://dlnext.acm.org/doi/epd... [acm.org]

    It appears the ACM PDF reader loaded an 850MB PDF into my phone's browser and has been stuck doing a search on "beam steering" for ten minutes.

    No joke, I read ACM papers on information retrieval and human computer action three decades ago and this is just hostile design.

    I'll try again on my desktop at home tomorrow but maybe somebody can extract the paper before then.

    And, yeah, as others have said this is old (November 2025) but

  • Sounds like they reinvented radar, maybe even synthetic aperture radar.

  • WiFi devices and routers can be used to create radio-based images of people and recognize them within seconds

    This, and the rendering in the linked article, give the impression that you can "see" the shape of a person using this technique. The reality is more like a heat map.

    So somebody might be able to use this to identify you, kind of like how they could look up your street number in property databases, check your mail, or collect your trash, to identify you. But they won't see you running around in your underwear (or worse).

  • Hasn't this been around a while? (Score:4, Interesting)

    by AlanObject ( 3603453 ) on Monday August 17, 2026 @03:34AM (#66292310)

    I went to an Intel Technology summit about 10 years ago (different world then) and one exhibit was showing off this capability. They had development kits with their chip set and software for sale.

    With just a few WiFi radios reporting in they did a pretty decent job of mapping everyone in the room. Of course it wasn't high-res enough to provide any identification details other that approximate size but I thought that was pretty impressive.

    This project doesn't seem to add anything new to that other than software that can distill more detail out of the combined signals.

  • This is something folks are working on for 6g -- integrated sensing and communication.
    https://www.qualcomm.com/resea... [qualcomm.com]
    Basically, hey, you've got all these devices pumping out signals everywhere at all kinds of wavelengths; if you receive and process them you can pretty much build a 3-D scene.

Slashdot Top Deals

(1) Never draw what you can copy. (2) Never copy what you can trace. (3) Never trace what you can cut out and paste down.

Close