Show HN: Glasses to detect smart-glasses that have cameras

10 hours ago (github.com)

Hi! Recently smart-glasses with cameras like the Meta Ray-bans seem to be getting more popular. As does some people's desire to remove/cover up the recording indicator LED. I wanted to see if there's a way to detect when people are recording with these types of glasses, so a little bit ago I started working this project. I've hit a little bit of a wall though so I'm very much open to ideas!

I've written a bunch more on the link (+photos are there), but essentially this uses 2 fingerprinting approaches: - retro-reflectivity of the camera sensor by looking at IR reflections. mixed results here. - wireless traffic (primarily BLE, also looking into BTC and wifi)

For the latter, I'm currently just using an ESP32, and I can consistently detect when the Meta Raybans are 1) pairing, 2) first powered on, 3) (less consistently) when they're taken out of the charging case. When they do detect something, it plays a little jingle next to your ear.

Ideally I want to be able to detect them when they're in use, and not just at boot. I've come across the nRF52840, which seems like it can follow directed BLE traffic beyond the initial broadcast, but from my understanding it would still need to catch the first CONNECT_REQ event regardless. On the bluetooth classic side of things, all the hardware looks really expensive! Any ideas are appreciated. Thanks!

Interesting idea. It seems to me that most things which would need to be protected from hidden cameras would be stationary and not require the operator to mount the detectors on his body, but starting with mobile constraints is often helpful.

I would like to draw attention to this gem of wit, easily the best I've seen in a long time:

> I think the idea behind this approach is sound (actually it's light)

  • It's me. I want to be protected from hidden cameras from other peoples glasses.

    • Project Codename: Allen Funt

      Project Description: Glasses that have a speaker and appropriately say “You’re on Candid Camera!” when it detects others being recorded.

  • Isn't the biggest mobile use case where you don't want to be secretly recorded in public? This was a big concern with the original Google Glass.

    • Massive problem in Japan where the issue of sex pests and covert recordings comes up every other day in the media. I suspect it's one of the reasons why Japan isn't on the list of supported countries for the Meta glasses. I hope it stays that way.

      1 reply →

    • The idea of being constantly monitored by a megacorp tracking all my movements wih their swarm of cameras to feed us personalized ads is utterly dystopian indeed.

      But I think the only valid way yo prevent this will be legislation though, it's not a fight individuals can win on their own.

      26 replies →

  • > most things which would need to be protected from hidden cameras would be stationary

    Counter-sniper systems that scan for reflections from optics have existed for twenty years already. These are indeed meant for static operation in military bases and other fixed installations.

  • I could see these being worn by walking-around security in a place where filming by the audience isn’t allowed. Super cool.

I think this generation will be remembered for how desperately it tried to cling onto privacy over our public image well beyond what should have been the reasonable time to acknowledge its passing.

I look forward to the social media rage meltdown shorts that widespread adoption of this tech will precipitate. I think I'm kidding. I should be kidding. But I am curious...

Question for people who resonate with this: whenever someone is holding their cellphone at an angle that "could be inferred" to be imaging you, how do you feel and think?

I grew up on Earth before the cellpocalypse (phone zombies, etc), and went through a stage of noticing all these new 'cameras' everywhere, but then I stoppped attending to it.

  • It's probably inevitable over time. "Smart" AR glasses that are indistinguishable from just a pair of regular glasses seem like something inevitable over the next decade or two.

I remember seeing some celebrities in the late 00s / early 10s with IR-emitting sunglasses or accessories to flood the camera sensors of paparazzi and make it harder for photographers to get spyshots of them.

Would this approach work for these camera glasses as well, simply flooding them with so much IR spectrum light that their sensors simply can't see you anymore?

  • Well, there's https://www.nii.ac.jp/userimg/press_details_20121212.pdf

    I think fooling facial recognition systems and CCTV-cameras-at-night is easier than fooling professional photographers. Most photograhers' cameras have IR filters, after all. And nobody's got an LED brighter than the sun.

    • On this topic, is there any benefit of trying to fool facial recognition systems with these type of accessories and or wearables, would the system not just mark you as suspicious and keep an even better track of you

      Of course it is a different thing if these are adopted by the masses

      1 reply →

  • One of my future ideas was to have the detection trigger turning a bunch of IR LEDs on to do just this! I've only tested it a little bit against my phone camera (with around 5 850nm LEDs), but it didn't work super well (fairly bright but not enough to be useful). It did work much better in low-light though. My guess is modern cameras have better IR-cut filters, but like I mentioned I only tested against my phone and not the Ray-bans yet.

  • That only works against night vision cameras. Most cameras have an IR filter that flips into place when when in daylight mode

  • I have been thinking of a device to thwart license plate readers by dumping a ton of IR and/or visible light on the plate before it gets read.

    Perhaps combined with some reflective coating? Retroreflectors are promising

    • Repo men use those readers to track cars to be repossessed. And as it happens, it is very successful industry these days.

    • Just as a heads up, this is likely illegal in many US states. (Legality is not morality - but it's good to know what the law is before you might break it).

  • I heard about similar hats being used during the Hong Kong protests, but most modern cameras filter out IR anyway. Reflective jackets tend to work much better; they basically turn you into an overexposed bright blob on camera.

  • What about correlating transmitted wireless frames with a LED flashing pattern? If the glasses stream video with a variable bitrate codec over wireless, flashing vs. non-flashing should change bandwidth and therefore frame frequency. However, with searching over all channels this might be quite slow in practice.

Semi-related question. Is there a method to print a picture on a t-shirt that can only be viewed by a camera and not be the naked eye? If so I would like to print images on the front and back of the shirt that would get the glasshole or cell phone cameras banned from their platforms.

Isn't there some kind of fluorescent effect that you can use? I.e., send one very specific wavelength onto the camera sensor, and receive one other very specific wavelength back.

I could see the guards at the courthouse, wearing these.

Cameras are so small, these days, that I don't think it's realistic to be able to detect them. I just go through every day, assuming that I'm on Candid Camera.

Does anyone work on smart glasses for blind people yet? Something with blackened glass, obviously, that uses image recognition to translate visual input into text via (headphone) audio to the wearer.

That would allow for urgent warnings (approaching a street, walking towards obstacle [say, an electric scooter or a fence]), scene descriptions on request, or help finding things in the view field. There's probably a lot more you could do with this to help improve quality of life for fully blind people.

  • I’ve heard stories of people using the Meta smart glasses to help with reduced vision, i.e. asking the LLM assistant what you’re looking at, asking it to read a label, etc. The LLM assistant can see the camera feed so it is capable of doing that.

    However things like the urgent warnings you mentioned don’t exist yet.

    Hearing about the way people with bad vision use these glasses kind of changed my viewpoint on them to be honest; for the average person it might seem useless to be able to ask an LLM about what you’re looking at, but looking at it from an accessibility standpoint it seems like a really good idea.

  • Every time I read about smart glasses I wonder the same thing. Obviously the technology isn’t perfect, but it seems that even a basic pair of smart glasses with primitive image processing could be life-changing for a completely blind person. Yet as far as I can tell, most blind people don’t use technology at all for this purpose.

    Unfortunately, the HN website is extremely unfriendly to users relying on assistive technologies (lack of ARIA tags, semantic elements etc.), otherwise there might be more blind people commenting here who could shed light on such things, no pun intended.

    • Makes me wonder just how big the market for such a device would be, and if it would attract investors…

  • If the top-level poster succeeds, the resulting device could possibly disable devices that allow blind people to see. This could open up another liability channel.

Comparable to what I read someone say about AI the other day: we're living in the small sliver of history where smart-glasses with cameras are technically feasible yet are still (kind of) detectable.

A much-needed project. Making yourself invisible to such privacy-invasive devices will be the need of the day. Of the two approaches you mentioned, blocking/jamming the specific wireless traffic would be pretty interesting, if possible.

  • > blocking/jamming the specific wireless traffic would be pretty interesting, if possible.

    And probably highly illegal.

    • Deauth attacks weer common in the Google Glasses days. Nobody got arrested as far as I can remember.

    • At the end of the day, legality is what society settles as an acceptable way of running itself when all the stakeholders reluctantly agree or at least don't protest too much. Right now the 'costs' are sufficiently low that no one cares. As with most things, I suspect that there is a threshold ( though likely much higher than I have previously anticipated ) at which normal person would be unwilling to go as if anything changed.

  • I'll feel much safer when I'm visible only to every single ATM camera, traffic camera, random smartphone camera and doorbell camera, but not to people's glasses.

Are there any smart glasses being developed for people with prosopagnosia or really bad face memory?

I often bump into people I know on the street but can’t place their faces. A lot of them get offended when I don’t immediately recognize them, even though I remember who they are—just not what they look like.

Sorry I'm still confused. Do you have a reliable way to detect if a smart glass is recording or not? I never used smart-glasses regularly, but wouldn't it be "on" all the time if one is using it, so detecting the power-on and pairing is kinda useless?

  • Regular pairing, advertising and control likley use Bluetooth LE for simplicity and battery life. Streaming or transferring video likley use Bluetooth classic for increased bandwidth.

    These are two different protocols with different radio behaviour.

    So beyond detecting the glasses themselves, which seem like the focus of the project; detecting recording is feasible at the point of transfer to a phone.

    The issue is distinguishing it from any other high bandwidth Bluetooth device nearby, such as headphones.

I love both names - ban-ray and ray-banned.

I have no experience in this area, so I’ll just ask a noob question: Can we make it so that if someone is looking at me through smart-glasses without my consent, my glasses respond with some form of interference that gives them a tiny headache?

And if I do grant someone consent to record me, I can just turn my glasses off.

And of course, my glasses don’t record anything, so they wouldn’t be hurting my own eyes.

Pretty neat idea! I love the BLE detection approach, would be pretty amazing if this works. I'll be following this with some interest!

  • Tangentially related it's also useful to quickly gauge if your smarts-wielding neighbors are home or not so noise levels can be adjusted accorsingly (:

Thank you for the technical write up. I have no expertise in the BTE area but it's clear enough for me to understand.

The swap pattern is very interesting but even if it's silly, maybe experimenting with an actual camera to detect cameras may give you a good base line to what to expect from a working Rayban banner.

I have a pen camera and a key fob camera. These are widely available. Obviously they won’t give you real time intel on what you’re looking at, but if you’re worried about being surreptitiously recorded, smart glasses are just a small part of the problem.

Super interesting project, at first I thought it would be a naive implementation of YOLO but I wasn't aware about retro-reflections. The papers he linked in the GH discuss very interesting ideas

It is interesting to see the consensus that nobody is enthusiastic about meta Ray-Bans except Zuckerberg.

It's creepy.

  • The only real usage I've seen is on Instagram reels etc. where people are using them in red light districts like in Amsterdam to film the women.

  • I have them and like them. I don't wear them constantly, but on days when I'm doing something interesting, they help me document much more than I otherwise would.

When I worked for a big Hollywood media conglomerate, there was a project to detect cameras in theaters. (There was a piracy problem where people would record the movie on a camcorder). It worked by detecting the IR filter that’s in front of the CMOS detector in almost all cameras. It’s a retroreflector for UV range. Shine a UV light to the audience and look for spots of light. I’d imagine this would work for cameras in any darkened environment even today.

Putting myself in the shoes of a qa for a second...

What is the cheapest way for me to trigger a false positive on such a detection device?

And what can we do about it?

Rinse and repeat until the cheapest cost exceeds a standard pair of smart glasses.

  • Before putting yourself in the mind of QA, you have to be 100% sure on what the goals and priorities of the product is supposed to be in the first place.

    Only a subset of use potential cases will be worried with false positives, but this approach says to drive the cost greater for all potential use cases.

  • Bluetooth packets similar to smart glasses and IR filters used by a popular brand should probably be enough.

I was thinking about this just the other day. You're on your way to implementing your own real-life stealth meter! Very cool!

That’s a really interesting project! It sounds like you’ve already explored some creative approaches with IR reflections and BLE traffic.

Taping over the recording indicator is illegal.

Is there any way your device can find the MAC address of the glasses through bluetooth or something and file a lawsuit automatically?