558
Humans can be tracked with unique 'fingerprint' based on how their bodies block Wi-Fi signals (www.theregister.com)
submitted 1 year ago* by to c/technology@lemmy.world
141 comments fedilink hide all child comments
 

The Sapienza computer scientists say Wi-Fi signals offer superior surveillance potential compared to cameras because they're not affected by light conditions, can penetrate walls and other obstacles, and they're more privacy-preserving than visual images.

[…] The Rome-based researchers who proposed WhoFi claim their technique makes accurate matches on the public NTU-Fi dataset up to 95.5 percent of the time when the deep neural network uses the transformer encoding architecture.

you are viewing a single comment's thread
view the rest of the comments
[–] 10 points 1 year ago (2 children)

When anyone or anything says that their product works "up to x%" I always presume it doesn't really work at all.
Christ, 1% is included in that "up to 95.5%" vague bullshit statement.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 2 points 1 year ago

    I believe the reason they had to say "up to" is because the "signatute" will vary day to day ever so slightly (natural weight fluctuation), and if you gain or lose weight it can change dramatically, so the AI would have to constantly consider that and adjust it's records.

    Honestly, unpopular opinion, but as long as it isn't very short wavelength RF and they allow for self-hosted/open-source alternatives, I do find it a bit more privacy respecting than cameras, of course they have to say they are using the technology in public places.

    It also has it's ways of fooling it, instead of wearing a wig and a false nose, you could wear a carbon-infused silicone fat suit to change the way you interact with RF.

  • permalink
  • fedilink
  • source
  • parent