Welcome • User Guide
ToS • Privacy • Canary
Donate • Bugs • License

©2026 Poal.co

273

Archive: https://archive.today/hJ5mG

From the post:

>Scientists in Germany have demonstrated a startling new form of surveillance: identifying people using nothing more than ordinary WiFi signals. By analyzing how radio waves bounce around a room, researchers can effectively “see” and recognize individuals — even if they are not carrying a device and even if their phone is turned off.

Archive: https://archive.today/hJ5mG From the post: >>Scientists in Germany have demonstrated a startling new form of surveillance: identifying people using nothing more than ordinary WiFi signals. By analyzing how radio waves bounce around a room, researchers can effectively “see” and recognize individuals — even if they are not carrying a device and even if their phone is turned off.
[–] • 4 pts

Yes. This is real, but every access point needs a model of identification. Cute, but can't be used for mass surveillance.

[–] • 1 pt

Yes, that's key that journalists don't cover adequately. The system has to be trained and told who is in the room and where (and presumably have them move around so it can learn what it looks like), THEN it can identify quickly. It would be like a security system using "AI" to show you a picture if your front door based on just the open/close sensor, after you give it photos of it being open and closed.

Devices on a wireless network regularly send feedback data known as beamforming feedback information (BFI) to the router. Because this information is transmitted without encryption, anyone within range can potentially read it. Researchers say these signal reflections can effectively create multiple "views" of a person, allowing AI systems to learn and recognize individual identities.

After the machine learning model has been trained, identifying a person reportedly takes only a few seconds.

[–] • 1 pt

This shit again? The FUD here always implies the technique is like what we see in (((movies))). The truth is that all it can really do is detect the presence of an individual but not identify them. This is not a detailed optical camera by any means and is more akin to a thermal imager but with even lower resolution. These are better ways of surveilling people inside a dwelling so being afraid of your WiFi is just the thing that they want to convince gullible people that they are being watched so that you'll police themselves. You already carry a tracking device so who gives a fuck if you can see a blob that represents the body that wears the tracking device?

[–] • 1 pt

It can detect (specific) people and -most- actions they are doing at any given time based on a few methods now. I have seen a (not public) system do this. I cant mention which because of NDA but it's way better than you think it is.

[–] • 1 pt

If trained with several people it can probably differentiate between them, but only in the same way that your bathroom scale can tell who's standing on it.

[–] • 1 pt

Sounds like niggers are safe from identification.

[–] • 1 pt

Yeah they did a proof of concept of this a while back…like 2-3 years.

But as you said, won’t work at any real scale

[–] • 1 pt

There is at least one github project I saw this week that is fully OSS that can do at least with the POC can do. I don't have the link handy though. It was posted to HackerNews.

[–] • 1 pt

Man I haven't been on HN in years. They banned me.