Humans can be tracked with unique 'fingerprint' based on how their bodies block Wi-Fi signals
Technology
140
Beiträge
101
Kommentatoren
15
Aufrufe
-
That's a false reading 1/20 times
And when has something like that ever stopped anyone?
Well okay you're not wrong, there is always some sucker out there.
-
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.
95.5% accuracy is abysmal for any use case these people want to use it for
-
Except that the tinfoil hats don't work
Maybe wearing a different tinfoil hat every day would mess up a person's "fingerprint"
-
wouldn’t that make it worse? basically any signal can bounce off you, making yourself even easier to track.
edit: wording
Since it 'figerprints' you, changing your fingerprint by blocking parts of the signal with pieces of foil doesn't seem like a terrible idea.
Now, the question is: is such a tactic like wearing gloves, or like using super glue?
-
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.I hate it when commercials say "up to 100%." It's literally a pointless metric; that could mean anything from 0% to 100%, inclusive.
edit: Closed quote.
-
The resulting image must just basically look like a shadow, I can't imagine that they're going to get much internal detail with Wi-Fi considering that my router's signal practically gets blocked by a piece of cardboard.
This research essentially amounts to, humans can be individually identified with nothing more than low quality x-rays. Well yeah, so what, you can also use visible light and in any situation where you're going to use Wi-Fi to detect someone, it's got to be easier to buy a cheap CCTV camera.
They explicitly went into the advantages over cameras:
- Any light condition (of course IR lighting with IR cameras are the gold standard so this can argueably be met otherwise)
- The ability to cover multiple rooms through walls with a device. A sub-10 GHz signal can penetrate most interior walls. People could be tracked without even being able to see a camera and by extension not knowing where to mess with to defeat surveillance.
So perhaps a building takes a picture of everyone as they come in the front door and also establishes a 'WhoFi' profile for that person. They could keep track of their movement through the building while maintaining an actionable correlation to a photo.
-
Why would someone research something like this? God damn, like use your life for good, homie
You think if people who publish their work publicly didn't research things like this, they would just never be discovered?
At least this way, we all know about the possibility, and further research can be done to see what can mitigate it.
-
accurate matches up to 95.5% of the time
and they’re more privacy-preserving than visual images
Oh fuck all the way off.
Sounds like an ad tailored specifically to putin
-
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 can also take a picture of a person with a camera that senses light beams
-
Maybe wearing a different tinfoil hat every day would mess up a person's "fingerprint"
you might be onto something.
take a mylar square and place it somewhere random on your body every day.
-
95.5% accuracy is abysmal for any use case these people want to use it for
what if you combine it with other types of imaging
-
what if you combine it with other types of imaging
Dingdingding
-
This shits already used by xfinity
WiFi Motion: Detect Movement In Your Home
Discover WiFi Motion and detect movement at home using your stationary smart devices, adding an extra layer of awareness to your everyday life.
Xfinity (www.xfinity.com)
Well, that’s quite different, it didn’t identify anyone
-
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.
This has me wondering how my sack of potatoes body would look
-
you might be onto something.
take a mylar square and place it somewhere random on your body every day.
Yep it has to be random to mess with the algorithm. You could have fun and cut different shapes each day.
-
First of all: cardboard does NOT block electromagnetic waves. You need a Faraday Cage for that. And even then, it has to have holes of a certain size to block specific wavelengths/frequencies. It’s why you have a mesh on the door of your microwave for example.
Secondly: they’re not attempting to photograph you. Just identifying your unique signature once would allow them to track your location anywhere where they have the gear installed.
EDIT: I suppose your comment is written in a way that it's not clear whether you're saying certain frequencies absolutely require meshes of a certain size to be blocked or if you're just adding that extra detail about the design of Faraday cages for the hell of it. But...
Original comment: It doesn't have to have holes to block radiation. A continuous sheet blocks all frequencies. A mesh is just nice so we can see through the cage or allow air to pass etc.
From the page you linked: "A Faraday shield may be formed by a continuous covering of conductive material." "... if the conductor is thick enough and any holes are significantly smaller than the wavelength of the radiation."
-
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 know, this, and the using wifi to see through walls stuff to me just immediately seemed to fall into "don't research this, it can only be used for evil".
I don't get why we bother studying these types of things.
-
I'm generally pro research, but occasionally I come across a body of research and wish I could just shut down what they're doing and rewind the clock to before that started.
There is no benefit of this for the common person. There is no end user need or product for being able to identify individuals based on their interactions with WiFi signals. The only people that benefit from this are large corporations and governments and that's from them turning it on you.
Continued research will ease widespread surveillance and mass tracking. That's not a good thing.
First - someone comes up with this. Next, privacy researchers and black/white/grey hat techies come up with methods to defeat it.
Better for surveillance tech research like this to be published out in the open than developed in some secret lab. I figure these researchers are doing more positive than negative by publishing their findings. It's not like if they didn't publish, someone else wouldn't come up with this and possibly use it clandestinely.
-
You know, this, and the using wifi to see through walls stuff to me just immediately seemed to fall into "don't research this, it can only be used for evil".
I don't get why we bother studying these types of things.
We study it because EVERYTHING can be used for good or evil.
If we'd stopped researching anything that could be used for evil we'd never have gotten into the stone age
-
The resulting image must just basically look like a shadow, I can't imagine that they're going to get much internal detail with Wi-Fi considering that my router's signal practically gets blocked by a piece of cardboard.
This research essentially amounts to, humans can be individually identified with nothing more than low quality x-rays. Well yeah, so what, you can also use visible light and in any situation where you're going to use Wi-Fi to detect someone, it's got to be easier to buy a cheap CCTV camera.
When they send a drone to your house they can make sure exactly where you are so they can shoot you through the wall.
