IBM Patenting Airport Profiling Technology

An anonymous reader writes "InformationWeek's Wolfe's Den reports that IBM has filed a dozen applications to patent a sophisticated airport security system which supports passive software-based profiling of potentially dangerous passengers off of pre-programmed rules. The setup uses a collection of sensors — video, motion, biometric and even olfactory — in terminals and around the airport perimeter, to supply raw data. 'These patents are built on the inference engine, which [analyzes sensor data and] has the ability to calculate very large data sets in real time,' says co-inventor Roger Angell. A small grid of networked computers delivers the necessary processing power. Two applications go one better than Israeli-style security, analyzing furtive glances to detect, according to the title of the patent application, 'Behavioral Deviations by Measuring Eye Movements,' as well as measuring respiratory patterns."

Israeli-style security

[Anonymous Coward]

I thought the Israeli "trick" were these long interviews face-to-face by trained humans looking you right in the eye.

I doubt 2 pieces of software are better than a trained human.

IBM has a track record

[Anonymous Coward]

after all, didn't they provide sophisticated technology for efficiently tracking and "managing" people who were not like the ordinary folks to a certain German government in the past ?

This is insane.

[flajann]

There is bound to be a high false positive rate with this system. Out of millions of people that will be profiled by this system per day, how many actual terrorist are there? Perhaps one or two a year?

Would actual terrorists behave or have other characteristics all that different that would definitively distinguish them from millions of others? I don't think so.

So really, in their efforts to find a needle in a haystack, many innocent people are going to be harassed.

Also, also with the needle in the haystack issue, I don't see this system effective in catching all actual terrorists, since they will be doing their best to "blend in" with the crowd and not stick out anyway.

So expect to have high failure rates of both type 1 and type 2 natures.

And so, the billions of dollars to deploy this system is justified how?

Not to mention all the civil rights issues with the government monitoring your biometrics without your consent or knowledge. Who knows what will be done with the data, and how it may affect you in the future? There are expectations of privacy violations here, which will be fought out in the courts.

Meanwhile, another "terrorist" will go "BOO", and you'll see hearings and blame-pointing and everything else at why this high-tech expensive system failed to catch the needle in a very big haystack "terrorist".

And now I am about to cause the paranoid US to spend billions more: BOO.

Re:The system works?

[ViViDboarder]

I don't think you're arguing with me, but just to be clear:

I do think the system right now works, but it can always work better. I firmly believe that things can always be made to work better.

That holds true for terrorist too. They can always come up with better and better ways to hide things. The thing is there is very little they can do about people getting nervous about their impending death as they prepair to blow themselves up. It's a great place to try and pick out people from the crowd and we're doing a damn good job, but there is always room for improvement.

Re:Money, Money, Money

[ViViDboarder]

Haha, yea. I realize that. I think people are smarter than keeping a weapon just tucked into their pants, but to anyone watching they don't know how well anyone is going to be patted down. Just the fact that they are stopping people is good because it just lets people know they are taking extra care to check people out. Some people more than others I guess.

Profiling

[Anonymous Coward]

Every last terrorist who has ever tried to hijack a US airplane has one thing in common: they are Arabs, they are Islamic, and they have brown to light brown skin. Why do we not give extra scanning etc. to people who fit this description as a matter of policy? So why are we stopping little old ladies and inspecting their bags? Why is profiling so wrong when we did not choose this enemy and cannot help that they all have so much in common that makes them so identifiable?

Re:The system works?

[digitig]

but it can always work better.

I agree, but we need to be careful about how we define "better". Security specialists will tend to define "better" as "more secure", no matter what happens to convenience or civil liberties. Passengers are more likely to consider "better" to be "more convenient", although they will want security to be adequate. Livertarians are likely to consider "better" to be "more liberty" or "more equality", with less regard for convenience or security. "Better" might be a case of finding a balance between conflicting interests that is more acceptable to the population as a whole, but in general it will be improving one or more criteria without significant detriment to the others.

The issue with profiling is what happens to the innocent that unfortunately match a profile. They are likely to be significantly inconvenienced, and the more we trust the profiling the worse it is likely to get for the false positives. The usual tendency of civilisation is to spread risk more evenly (eg, insurance) as well as reducing it. Unless it is extraordinarily well implemented, profiling goes against that trend, making things better for the majority but making things very much worse for an unlucky few.

Re:The system works?

[Gravitron 5000]

Livertarians are likely to consider "better" to be ...

... with onions.