It would be very hard to conceal such conformally-packed explosives from sniffers and dogs.
Pornoscanners trivially defeated by pancake-shaped explosives
11–20 of 37 posts
Re: Pornoscanners trivially defeated by pancake-shaped explosives
#12Admittedly early for me, but I read the headline very differently.
Re: Pornoscanners trivially defeated by pancake-shaped explosives
#13Wow. There is a "Journal of Transportation Security"...
Re: Pornoscanners trivially defeated by pancake-shaped explosives
#14I'm against security theater, but this sounds like an information visualization problem: if the image contains enough signal that a theoretically optimally trained eye can detect the contraband, they should be able to use machine learning algorithms to detect suspicious items and make them show up with higher contrast.
In other words, the software should magnify anything out of the ordinary, like contraband. It's not foolproof of course, but would help.
Re: Pornoscanners trivially defeated by pancake-shaped explosives
#15I'm against security theater, but this sounds like an information visualization problem: if the image contains enough signal that a theoretically optimally trained eye can detect the contraband, they should be able to use machine learning algorithms to detect suspicious items and make them show up with higher contrast. In other words, the software should magnify anything out of the ordinary, like contraband. It's not…
I think the issue is that if you can produce anything approximately the size and density of a gut, you can get it past a scan - no machine learning is going to be able to pick up something that for all intents and purposes looks like a normal beer belly.
Re: Pornoscanners trivially defeated by pancake-shaped explosives
#16Cut the foreplay, TSA, we all know eventually we will have to get on the plane naked!
After a good cavity search.
Because, let's face it, all it takes is one bra-bomber and panty-bomber for this to become a reality.
Re: Pornoscanners trivially defeated by pancake-shaped explosives
#17Cut the foreplay, TSA, we all know eventually we will have to get on the plane naked! After a good cavity search. Because, let's face it, all it takes is one bra-bomber and panty-bomber for this to become a reality.
Cavity searches aren't profitable.
Re: Pornoscanners trivially defeated by pancake-shaped explosives
#18I'm against security theater, but this sounds like an information visualization problem: if the image contains enough signal that a theoretically optimally trained eye can detect the contraband, they should be able to use machine learning algorithms to detect suspicious items and make them show up with higher contrast. In other words, the software should magnify anything out of the ordinary, like contraband. It's not…
They aren't meant to detect explosives.
They are meant to detect weapons that the metal detector might not pickup
The explosive you would just put through the x-ray machine anyway where it wouldn't be detected.
Re: Pornoscanners trivially defeated by pancake-shaped explosives
#19I'm against security theater, but this sounds like an information visualization problem: if the image contains enough signal that a theoretically optimally trained eye can detect the contraband, they should be able to use machine learning algorithms to detect suspicious items and make them show up with higher contrast. In other words, the software should magnify anything out of the ordinary, like contraband. It's not…
Sorry, but what you're suggesting is the equivalent of "every airplane should fly flapping its wings"
"if the image contains enough signal that a theoretically optimally trained eye can detect the contraband, they should be able to use machine learning algorithms to detect suspicious items and make them show up with higher contrast."
The type of processing which you'd run on an image to make it easy on the human eye is entirely different than what you'd do for ML applications.
Re: Pornoscanners trivially defeated by pancake-shaped explosives
#20I'm against security theater, but this sounds like an information visualization problem: if the image contains enough signal that a theoretically optimally trained eye can detect the contraband, they should be able to use machine learning algorithms to detect suspicious items and make them show up with higher contrast. In other words, the software should magnify anything out of the ordinary, like contraband. It's not…
I think the issue is that if you can produce anything approximately the size and density of a gut, you can get it past a scan - no machine learning is going to be able to pick up something that for all intents and purposes looks like a normal beer belly.
Fully agreed that that's a real problem.