social.sokoll.com

#AI #surveillance #escape

This colorful printed patch makes you pretty much invisible to AI - The Verge



The rise of AI-powered surveillance is extremely worrying. The ability of governments to track and identify citizens en masse could spell an end to public anonymity. But as researchers have shown time and time again, there are ways to trick such systems.

The latest example comes from a group of engineers from the university of KU Leuven in Belgium. In a paper shared last week on the preprint server arXiv, these students show how simple printed patterns can fool an AI system that’s designed to recognize people in images.

If you print off one of the students’ specially designed patches and hang it around your neck, from an AI’s point of view, you may as well have slipped under an invisibility cloak.

As the researchers write: “We believe that, if we combine this technique with a sophisticated clothing simulation, we can design a T-shirt print that can make a person virtually invisible for automatic surveillance cameras.” (They don’t mention it, but this is, famously, an important plot device in the sci-fi novel Zero History by William Gibson.)
No, not really. It's a pretty simple edge case for image recognition. All you have to do is add that edge case to training data and you are ID'd too. For an example, look at the recent video from Tesla regarding bicycles attached to the back of vehicles.
https://pluspora.com/posts/1200784 - look at the link on Neural Network Essentials.
Also, The Verge has a pretty bad track record for misinterpreting or misrepresenting AI capabilities.
Yup, even before reading I thought it was just a matter of training.
It's always a matter of training. In fact it's an endless race between those who exploit weaknesses and those who retrain or patch the specific weakness.
This one is a very specific weakness of just one algorithm, the article makes it clear.