Engineers Say They've Created Way To Detect Weapons Using Wi-Fi (gizmodo.com) 91
An anonymous reader quotes a report from Gizmodo: The researchers, which include engineers from Rutgers University-New Brunswick, Indiana University-Purdue University Indianapolis (IUPUI), and Binghamton University, published a study this month detailing a method in which common wifi can be used to easily and efficiently identify weapons, bombs, and explosive chemicals in public spaces that don't typically have affordable screening options. The researchers' system uses channel state information (CSI) from run-of-the-mill wifi. It can first identify whether there are dangerous objects in baggage without having to physically rifle through it. It then determines what the material is and what the risk level is. The researchers tested the detection system using 15 different objects across three categories -- metal, liquid, and non-dangerous -- as well as with six bags and boxes across three categories -- backpack or handbag, cardboard box, and a thick plastic bag.
The findings were pretty impressive. According to the researchers, their system is 99 percent accurate when it comes to identifying dangerous and non-dangerous objects. It is 97 percent accurate when determining whether the dangerous object is metal or liquid, the study says. When it comes to detecting suspicious objects in various bags, the system was over 95 percent accurate. The researchers state in the paper that their detection system only needs a wifi device with two to three antennas, and can run on existing networks.
The findings were pretty impressive. According to the researchers, their system is 99 percent accurate when it comes to identifying dangerous and non-dangerous objects. It is 97 percent accurate when determining whether the dangerous object is metal or liquid, the study says. When it comes to detecting suspicious objects in various bags, the system was over 95 percent accurate. The researchers state in the paper that their detection system only needs a wifi device with two to three antennas, and can run on existing networks.
Re: (Score:2)
I imagine if you were to do a cost comparison, it would compare rather well.
This likely isn't meant as a replacement for x-ray inspection machines, but could be a good solution for public venues such as concerts, stadiums, schools, etc.
They forgot..... (Score:2)
They forgot I think to think about the trivial countermeasures, like lining the suitcases with aluminum foil, or using aluminum suitcases, or putting absorbent ferrite sheets in instead. You can't see what doesn't reflect or reflects all or absorbs a lot.
Re:They forgot..... (Score:5, Insightful)
I always figured the way to beat baggage screening was a kind of x-ray stenography. Pack your contraband items in close proximity to familiar and non-contraband items that are readily identifiable to x-ray screeners. Unless its entirely obvious, they will just assume the contraband is another similar item to what they can "see" and let it pass, or the item density and overlap will be such they can't quite make out anything and might just assume it's a collection of toiletries or some other innocuous content.
Of course I just made this all up and don't have any experience in smuggling, so perhaps this is all just errant speculation.
Re: They forgot..... (Score:1)
This. I used to smuggle Xanax pills in aspirin bottles.
Re:They forgot..... (Score:5, Funny)
I would think x-ray steganography would be a lot more useful. That is, unless you're arranging your contraband items in the shape of shorthand.
Re: (Score:3)
I used to pack my shampoo in the top of my garment back where it was surrounded by a dozen or so hangers.
Never had an issue.
Re: (Score:2, Insightful)
> trivial countermeasures, like lining the suitcases with aluminum foil
Yes, because having a suitcase lined with aluminum foil is totally benign.
> You can't see what doesn't reflect or reflects all or absorbs a lot.
No, but you can make a note of something that DOES all those things. Normal suitcases don't.
Re: (Score:2)
Until I start selling them. "Keep your private things private." Show a lady being embarrassed by cops pulling out her gun shaped dildo. "Buy CastroTech Luggage."
Re: (Score:2)
Re: (Score:1)
Nah. If the baggage inspectors can't detect what's in the suitcase with their machines, they'll just open the suitcase. With a five-dollar wrench, if need be.
Easy Solution (Score:5, Insightful)
They forgot I think to think about the trivial countermeasures
Not really because these have trivial solutions: just flag any bag which shows a huge amount of reflection or none at all as suspicious. Then, instead of a quick automated scan, you can be detained by security and wait while they rummage through your bag.
Re: (Score:3)
This is precisely why I get stopped at the airport for an additional check. I often carry large lenses through in hand baggage and at Schiphol they happily show you a picture of your bag, including the fact that you can't see anything in most of the bag when the bag is filled with large chunks of glass.
Re: (Score:3)
The answer to that: "I'm sorry sir, we're going to need your consent to open your bag. If you don't give your consent, feel free to not enter the building / concert / stadium / whatever."
Terrifying (Score:5, Insightful)
Re: (Score:2)
Re: (Score:3)
"In this work,
we leverage the fine-grained channel state information (CSI)
that is readily available in low-cost WiFi devices to detect
and identify suspicious objects hidden in baggage without
intrusion (e.g., opening the bag)."
Re: (Score:2)
Re: (Score:3)
>"low-cost WiFi devices to detect and identify suspicious objects hidden in baggage without intrusion (e.g., opening the bag)."
I guess that depends on one's definition of "intrusion" because I consider searching me or my stuff without probable cause to be intrusion, whether you do it with a physical search or some automated one at a distance. In fact, the latter is probably WORSE because it enables far more searching and the real possibility of it being done clandestinely.
And, of course, just about anyt
Re: (Score:2)
And mind you that a bad actor can divise a means to make something go off when exposed to certain frequencies.
A "bad actor" who has a trigger go off when exposed to 2.4GHz WiFi signals is also a "bad designer" and then a "bad dead person". Since it will probably trigger in his own residence, he's also a "bad tenant" or a "bad risk for a home loan".
He would be a "good terrorist", however, since blowing himself up in his livingroom isn't very terrorizing, and we already know that the only good terrorist is a dead terrorist.
Re: (Score:2)
>"He would be a "good terrorist", however, since blowing himself up in his livingroom isn't very terrorizing"
LOL!
Re: (Score:2)
Re: (Score:2)
The person who shoots an innocent citizen is mo
Re:Terrifying (Score:5, Informative)
Re: (Score:2)
Re: (Score:2)
The concern isn't what a handful of s
Re: (Score:2)
Yeah, this requires a specific device that uses specific metrics of the radio waves to do what it does. You can't just turn some shit on in someone's off-the-shelf-at-Bestbuy router and image their whole house.
Paranoid much?
Re: Terrifying (Score:2)
Re: (Score:2)
Physics called and said that you don't know what the fuck you're talking about.
Re: (Score:2)
Now another team looks in with wifi to map out the location from the outside in.
there's an APP for that! (Score:3)
Re: (Score:2)
Signal reflectivity and object characterization is fairly evolved. 1-5% error is pretty clever, but it stands to get more testing, as the madness of what people bring in terms of metallic contraband is huge.
Might it mistake a flask of booze rather than suntan lotion? I'm not sure. Could a big hunk of metal be mistaken for a pistol? Again, not sure. They have to prove effectiveness, or the litigation potential could make many lawyers really rich.
Before a commercial deployment, I'm betting there are guideline
This isn't WiFi as such. (Score:5, Insightful)
Re: (Score:3)
Basically a more advanced metal detector.
... aaaand now I'm trying to figure out how to rig it for finding gold nuggets in the earth...
Re: (Score:2)
Basically a more advanced metal detector.
... aaaand now I'm trying to figure out how to rig it for finding gold nuggets in the earth...
And my first thought is that it wouldn't have much use with a 2' range. Then I started thinking about placer deposits in river bed rocks. Might be able to use it to determine if an area was worth digging up into a mining sluice. Of course, I have no real clue to the realities of prospecting for placer gold...or how these wifi things work.
Re: (Score:1)
So it's basically sneaky marketers renaming existing stuff, such as "agitation engineer" instead of "troll".
meaningless measures (Score:5, Interesting)
Re:meaningless measures (Score:5, Interesting)
Not just that, but it was 15 samples and they knew what was in the bags/boxes. Talk to me when they've done a thousand samples in a double-blind environment with real packed luggage that contains all the weird shit people put in bags like prescriptions, breast milk, vibrators, etc that the "scanner" operator has no idea what's in each bag.
They ran off and claimed 95%+ detection and they've got no evidence at all of that kind of reliability. Scanning bags for dirt simple things like guns is hard, and scanning for anything like explosives is 100x as hard.
Step two. (Score:2)
Time to fire the TSA! ;)
Re: (Score:1)
The time to fire the TSA was the day it was created, along with the moronic self-serving politicians that created it.
Re: (Score:2)
Step 3: Profit!
Percentage errors (Score:5, Insightful)
Even 99% accurate is absolutely horrid for real-life situations. Let's take a case where one in a thousand items encountered are dangerous. I'm going to scale the numbers to make the results come out as integers. At 1 in 1000, if we start with 100,000 items we'll have 100 dangerous items and 99,900 non-dangerous. Of the dangerous items, the system will flag 99 as dangerous and 1 as non-dangerous. Of the non-dangerous items, the system will flag 98,901 as non-dangerous and 999 as dangerous. So out of 1,098 items flaged as dangerous, 90.98% of them will be non-dangerous. So a system that claims a 99% accuracy rate will have a 91% error rate when it comes to sounding the "Danger!" alarm. Only 9% of the time will that alarm actually indicate danger, the other 91% of the time it's a false alarm.
The above is why 5-nines (99.999% accuracy) is the baseline for workable systems.
Re:Percentage errors (Score:5, Informative)
You apparently don't understand the failure rate of traditional TSA detection methods: https://abcnews.go.com/US/tsa-fails-tests-latest-undercover-operation-us-airports/story?id=51022188, and that is for airports.
Re: (Score:2)
I go to a festival, they search every bag for liquid, with I don't know what kind of a failure rate, but it's more than 1% of the bags of wine wrapped in towels that get through.
With this system, they can more thoroughly search 1% of the bags, and only have 1% get through.
Seems like it could be useful to me.
Re: (Score:2)
Re: (Score:2)
The above is why 5-nines (99.999% accuracy) is the baseline for workable systems.
There are no systems in the world meeting your imaginary requirements.
Don't let perfect become the enemy of good.
iGun (Score:5, Funny)
That's why I always put my iRifle on airplane mode when I don't want to be detected.
weird (Score:1)
Can it find combustable lemons? (Score:2)
It can't hurt to ask.
Nothing new here (Score:1)
A cool experiment, not a practical solution (Score:4, Insightful)
Unfortunately, the reporting is lacking in highlighting this. I suspect, frankly, because those reporting on it don't really understand what they're looking at.
The method of detection in this case is rather crude. In reality, no fancy countermeasures are necessary. Take your contraband item and simply enclose it in the shape of something harmless, and this system would be immediately fooled.
Re: (Score:2)
It's worse than that. They used wifi because that's what they had at hand. It had nothing to do with computers, only with having electromagnetic response on a certain spectrum.
The article doesn't understand anything about the practicality of the study, nor the real technologies, and don't care a bit because they want clickbait articles to make money. The fact that this study is relayed (out of maybe hundred of others) is actually because they used wifi devices for their experiments, which people know and u
Re: (Score:2)
New police radars can 'see' inside homes (Jan. 19, 2015)
https://www.usatoday.com/story... [usatoday.com]
Technologies that see through the walls (July 7, 2015)
https://www.kaspersky.com/blog... [kaspersky.com]
Sounds like tomography (Score:2)
There's nothing particularly new about tomography. It's been known abou
Pandora's box ... (Score:2)
... because it will be monetized.
"Psst ... wanna buy newer underwear?"
Re: Pandora's box ... (Score:2)
Fun things to do at an airport (Score:2)
Mold crushed up aluminium foil in the shape of a gun and put it in your carry on bag, watch the expression on the face of the xray operator!
Re: (Score:2)
and put it in your carry on bag
No. We're putting it in your carry-on bag.
Re: (Score:2)
That would be illegal, smuggling an item in someone else's bag.
I don't advocate being a criminal.
Real use case (Score:2)
Seriously? (Score:2)
well article not complete, (Score:2)