Just got doxxed to within 15 miles by a vision model, from only a single photo
1–10 of 67 posts
Re: Just got doxxed to within 15 miles by a vision model, from only a single photo
#2Well that's horrifying
Re: Just got doxxed to within 15 miles by a vision model, from only a single photo
#3How well would it work if the scenery is not from a road mapped by Google Street View? Like in, the actual nature?
Re: Just got doxxed to within 15 miles by a vision model, from only a single photo
#4Aren't there GeoGuesser types who can do this without a model? Some knowledge of vegetation goes a long way.
Re: Just got doxxed to within 15 miles by a vision model, from only a single photo
#5Aren't there GeoGuesser types who can do this without a model? Some knowledge of vegetation goes a long way.
Yea but I guess AI makes it cheaper and more available. Just like photoshop pros could make fake photos before AI but now anyone can do it in 5 sec with a prompt.
Re: Just got doxxed to within 15 miles by a vision model, from only a single photo
#6At the risk of sounding stereotypically skeptical, how do we know there's not a person behind the AI curtain, geo-guessing?
Re: Just got doxxed to within 15 miles by a vision model, from only a single photo
#7How well would it work if the scenery is not from a road mapped by Google Street View? Like in, the actual nature?
I tried some old phone photos from my grandparent's rural Canadian farm and it either got the province wrong or it guessed Montana or North Dakota.
Re: Just got doxxed to within 15 miles by a vision model, from only a single photo
#8Aren't there GeoGuesser types who can do this without a model? Some knowledge of vegetation goes a long way.
[dead]
Re: Just got doxxed to within 15 miles by a vision model, from only a single photo
#9How well would it work if the scenery is not from a road mapped by Google Street View? Like in, the actual nature?
there are services for photo sharing with location data (panoramio for example) that could be used for training.
Re: Just got doxxed to within 15 miles by a vision model, from only a single photo
#10How do they know it’s not from EXIF data?