It’s a satire account btw
It’s a satire account btw
Too bad! 🥹
Yeah I could tell from the pride colors of the Sherrif Dept logo lol
Seriff*
Hong Kong protesters started using camouflage to stay anonymous after police started using facial recognition camera’s: it turns out, it is only useful if you can also hide your camouflage. They needed to be able to blend in to avoid being caught. The idea seems great, but even if this would be done for real it would not be good enough unfortunately.
Dress in black so you blend in with the spraypaint covering the camera lens.
The problem is…then what? Are you going to walk from your front door to the flock camera, all in full black clothing and face coverings? You’re going to have to walk past any closed-circuit security and Ring doorbell cameras. Police can follow you through multiple cameras and maybe even see you walking through your front door.
Are you going to drive a few blocks from the camera, park, and then walk to it? They can search vehicle position records for any vehicles that came and left within a certain distance from the cameras within a certain time period. If they can trace you walking to your car, they can find you. Even if you left your phone at home and use an old vehicle without spytech in it, there will still be video of your vehicle in the area.
Flock cameras are probably the single most capable cameras police departments have regular access to. But they have access to countless tools of surveillance. I think the only way you could reliably damage a flock camera and get away with it is if a Flock camera is near some nature area or other natural feature. For example, if there’s a forest area a short distance from where the camera is, or a stretch of tree-covered river or creek you could duck into to break the camera track.
In order to destroy a flock camera and get away with it, you would need to have access to some large area that is not under surveillance. This allows you to walk into the area while in plain clothes, change into concealed clothing while in the area, and the reverse on the return trip.
Destroying a flock camera while keeping your face covered is trivial. The hard part is getting to the camera and getting back home without leaving a trail to your identity. And unless there’s a big nature area nearby you can disappear into, I think that would be a challenge.
Notably, this is actually the technique Luigi used. He ducked into a wooded park to change clothes and escape the surveillance net. With enough resources they were still able to catch him. But someone destroying a flock camera won’t justify as much resources to hunt them down as what Luigi did.
It was a joke, I think you skipped over the second half of the sentence.
Hmm. That does appear to be the case! 😂
They, could do all of those things, in theory.
In the fantasy land where they’re as capable as their fascist tools, and the tools themselves are as good as they advertise.
There are already dozens to hundreds of people getting away with the destruction of Flock cameras. They literally ask for public tips to solve them.
Have you read the research on the actual impact of all this bullshit on crime rate solving?
The panopticon is not finished.
Until it is, large swaths of your comment might as well be fiction, because until it’s trivial to “justify as much resources to hunt them down as what Luigi did” for the average use, they literally can barely find their ass with them.
Apparently clown makeup, specifically Juggalo makeup, used to be good at confusing facial recognition.
Benn Jordan did this with license plate readers. The stickers were invisible to casual observation, but the cameras couldn’t reliably decode anything from them.
I think it used bits of IR vinyl.
Is IR reflective makeup a thing?
Looks to not be. IR reflective sunscreens and foundations would probably sell fairly well
IR doesn’t hurt your skin like UV, but it would keep you cooler I think.
its probably possible to have inconspicuous patterns that get interpreted in same way as clear picture
What’s is your point about HK? Why always point directly at China? What about the Gestapo you call ICE with their face masks? What about flock cameras in the US being used to track ex wives or girlfriends?
It’s a satire account btw
The fact this needs to be pointed out shows the level of the users here.
I’d already covered my whole car before reading the post description 🤦♂️
Don’t do this to your vehicles. A) it doesn’t fucking work. B) It’s meant to trick you into making yourself an easily identifiable target for law enforcement.
The best thing you can do is avoid the cameras when possible and make your car as bland as possible (no stickers, no identifying features). These systems suck, lean into that fact. Also a little “accidental” splattered mud on the license plate doesn’t hurt either. Not enough to prevent a person from reading it, but just enough to break the AIs brain.
A) it doesn’t fucking work
Have you done actual testing against multiple cam types, including Ring and Flock?
This guy has, he presented at BlackHat. And yes, it works
They’ll never be able to spot it now!
It doesn’t break the camera like the post suggests, however. It just prevents them from registering it as a vehicle.
Here are some people at DEFCON who have been making low-cost devices for identifying the radio fingerprint of nearby flock cameras: https://youtube.com/watch?v=-2uAsJ5EPAw
Which is cool, but also the cameras aren’t exactly inconspicuous. You can easily see them well before you’re in bluetooth range. Or just check deflock.
They’re hiding some of them now.
Plates that can’t be read by software gets sorted for human input, splattering it doesnt help unless its completely unreadable.
Get an electromagnet and put behind your plates instead with a fake leaf that disappears anytime you get pulled over
Knowing that the state that submits the image for human review is that the system must automatically (1) identify a car (2) whose license plate can’t be automatically read, the more productive trickery would be to defeat the “identify a car” part where the software doesn’t even know that a car drive within its field of view, and therefore doesn’t know to take a still frame and forward it to a human.
Alternatively, have the software automatically read a license plate incorrectly so that it doesn’t trigger human review but is instead confidently incorrect in what it did log to the records.
What about those UV lights on the tag? I’ve wondered about using those
This will not work. AI-enabled surveillance cameras are more than capable of determining that it’s a wrap on a car, rather than multiple cars all somehow moving in the exact same direction in the exact same area while all facing in incorrect directions relative to the camera.
If anything, it’s just another data point, because Flock cameras also catalog details about your vehicle like stickers, color, wraps, graffiti, dents, etc.
Wonder if covering in a design that looks like you are covered in plates would do anything. Like blurred rectangles that sorta look like a particular states plate and then random numbers. Is it illegal to cover your car in numbers?
How about QR codes?
No way that Flock cameras have good enough resolution to be able to tell that those are pictures of cars. Not even close.
Select all the images that have cars
This square has a tiny sliver of a fender. Does the system count that as a car?
The car version of the ahegao hoodies we all wear to fool facial recognition.
It’s great to see little Bobby Tables’ car wrap business taking off. I need to make an appointment!
It’s car-ception!
Oh this gives me an idea…
At the very least it would be a statement on how sick of being surveilled we are.
As silly as this is, with access to the exact model flock uses for vehicle recognition, it might be possible to design a camouflage paint job that confuses the classification pipeline
Benn Jordan made a video outlining his experiments around this topic. Good stuff.
i doubt that would work, just knowing what i know about stuff like opencv let alone proprietary things like cognex/precise.
There are patterns that these cameras cannot parse.
They either discard the image or flag it for a human, depending on the configuration.
The reason this works is that these AI bots are trained on solid color cars and car shapes.
Eventually this might stop working, if only because these models are constantly being trained in more and more of our data.
it doesn’t necessarily have to be an “ai” model just machine vision custom tuned. on yes, gobs of data. :(
