defend yourself against flock cameras with this simple trick

165 points · 8 comments · view on lemmy.world

8 Comments

hendrik@palaver.p3x.de · 36 pts · 278d (6 replies)

Nice idea. Unfortunately this doesn't fool ChatGPT... "The picture shows an apple with a piece of paper taped to it that says “iPod.” It’s a visual joke: the apple is being humorously labeled as an “iPod” (since Apple makes iPods), creating a pun."

otacon239@lemmy.world · 19 pts · 278d (5 replies)

Flock would be using a local model, so this might actually be pretty effective.

sugar_in_your_tea@sh.itjust.works · 4 pts · 278d

Yeah, you'd need to do a FOIA request to check if it worked.

hendrik@palaver.p3x.de · 3 pts · 278d (2 replies)

Sure. I mean realistically we need something for real-world application, like sunglasses form factor with the category "innocent citizen doing harmless stuff" or "criminal" taped to it, to fool the systems which are currently being rolled out. But I have no clue what amount of computing power they use for license plate readers or to spy on the pedestrians in the city center / mall / train station / bad neighborhood or wherever these AI cameras are being used.

otacon239@lemmy.world · 10 pts · 278d (1 reply)

This video may help shed some light (as well as an already proven method to fool them): https://youtu.be/Pp9MwZkHiMQ

hendrik@palaver.p3x.de · 1 pts · 278d

Lol, I was just adding the youtube video I watched yesterday to my previous comment: Can I Confuse Police AI Cameras? about road safety cameras in Australia(?), and seems they use some amount of processing power. Or human oversight. At least he doesn't get a ticket in the end. But that was just a mostly humorous take on a similar thing. Thx for the video on Flock cameras.

Xylight@lemdro.id · 1 pts · 276d

This isn't actually using a vision LLM, it's using a CLIP model. This image comes from an OpenAI blog from 2019 I think

Mk23simp@lemmy.blahaj.zone · 6 pts · 278d

TF2 Spy disguise