World's Most Accurate Lie Detector 55
An anonymous reader points to this "interesting article about the world's most accurate lie detector. It seems they are getting real close to Voigt-Kampff. Watch out fellow replicants."
This discussion has been archived.
No new comments can be posted.
World's Most Accurate Lie Detector
Related Links Top of the: day, week, month.
He has not acquired a fortune; the fortune has acquired him. -- Bion
Now's the time to confess, while you still can! (Score:2, Funny)
I'm the one, it was me all along, I put the rubber snake on Mrs. Montgomery's chair in Grade 3!
I invented New Coke!
I shot J.R.
...and I came up with the idea for Pop-Under Advertising!
I throw myself on the mercy of the /.court
Re:Now's the time to confess, while you still can! (Score:5, Interesting)
No need for the premature capitulation.
Just get botox injections like poker players do.
I would bet that politicians will soon start to emulate aging soap stars and get them too.
How soon before a newspaper pays to have some footage analyzed? How soon before tabloids say they have had some footage analyzed?
I also would not be surprised if there popped up a service that taught you how to beat the new system, for the right fee. Look at all the effort used to defeat urine tests for drugs...
Re:Now's the time to confess, while you still can! (Score:2)
http://www.ananova.com/news/story/sm_531596.htm
Polygraphs are shit and this is slightly better (Score:4, Informative)
Perfect (Score:1, Funny)
It's like in "Liar Liar" where he cannot tell a lie. Personally the first thing that I would have done is to read out lots of physics theorys and see which are correct.
If they are wrong, then I'm lying, so the machine should beep me. I'll become famous!
Re:Perfect (Score:2, Insightful)
Re:Perfect (Score:4, Insightful)
Pinocchio (Score:1)
Imagine if they were 100% perfect!
Carlo Collodi imagined it for you, in a novel called The Adventures of Pinocchio [everything2.com]. An intelligent puppet is built (Spielberg's A.I. was based partly on this and partly on "Supertoys"), and a lie detector is implanted in the nose.
Scary (Score:5, Interesting)
Clinton (Score:3, Interesting)
Anyway, they said that experts had looked at videos of clinton telling everyone that he hadn't had sexual relations, and that the experts had all said he was a very bad liar, and it was really obvious..
Dunno how true this is...
Re:Clinton (Score:3, Insightful)
You do realize that if this is really what they said then they are full of shit, right? While there may be some truth to the idea that one side of the brain is responsible for a certain kind of thinking and the other is responsible for the rest, it's definatly not the same side for everybody. Also, some people can use both sides effectively for everything.
Like this would work... (Score:3, Insightful)
That would be illegal within a month.
Re:Like this would work... (Score:1)
Re:Like this would work... (Score:1)
I don't see why knowing if someone is telling the truth should be illegal!? Can you all imagine what Washington DC would be like if a "Liar Liar"-like scenario applied to all members of Congress?
Re:Like this would work... (Score:1)
Wouldn't be hard to cheat some false-positives, either, with current video editing technology. With only a few intentional false-positives turned into slander suits, a mediocre team of lawyers could scare the press from ever trying to use the technology like that.
Predictions (Score:5, Informative)
If it turns out to work, it will be banned for use on TV during politicians' speeches. (The first amendment will be found not to apply.)
Expect to see software that can edit out the facial gestures, in real time. Politicians will only release footage that has been filtered by it in their own offices.
Software that detects that filtering will be banned.
Problem with all such devices: (Score:5, Insightful)
I have observed that many of the tests of these devices involve studies where the subjects are encouraged to fool or beat the machine and they base their results on that. However, the subjects are probably already familiar with the tests and are (I imagine) not in fear that something bad will happen to them if they fail.
In the case of the proposed settings (airports, police station), failing this lie detector test could lead to Bad Things. I wonder if these machines pick up the facial features that arise when "the subject is making an attempt to provide a satisfactory response" and THIS mental activity causes the facial feature changes the trained AI responds to.
I suspect the AI was created by evolving a neural net based on human trials (2-layered? -they even mention that it monitors 24 channels; this wouldn't take too long to evolve). Hence it is trained to the testing conditions, and these premises of what they are testing, and/or the methodology of the training may be incorrect.
Maybe the question really is: do we care that the device may be responding to mental stress vs. truth/lie telling? Some might consider it more useful that it just measures stress (which in a question and answer session can be caused by fabricating responses). It could indicate when someone should have a "bad feeling" about someone or their claims. At the same time I feel that if my allegations are true, this device also should (in addition to standard polygraphs) not be used to generate evidence for trial proceedings.
Anyone with more insight into this care to add?
Re:Problem with all such devices: (Score:4, Interesting)
There's a theory that the knowledge that you're lying evokes some cognitive thoughts that sort of "leak out" into your facial expression. You can be nervous on the one hand, but still show micro expressions when you lie. Maybe a very fast curl of the muscles between your eyes, or the flip of an eyebrow, or a slight quivering of your lower lip. They're much, much faster than signs of nervousness...
Re:Problem with all such devices: (Score:2)
Dangerous stuff (Score:5, Insightful)
Polygraph administration and analysis turns out to have huge subjective factors despite attempts to appear otherwise. Some people are especially accomplished liars; it doesn't hurt to be a sociopath who really doesn't have any emotional reaction.
Perhaps this system will have some use -- let's remember that even the standard Voight-Kampff got beat! (why did Deckard press on with 2x more Q's?) -- but I hope it and other techno-gadgets don't lessen emphasis on good old-fashioned security and common sense.
Re:Dangerous stuff (Score:5, Insightful)
Polygraphs have not, in fact, been "barred" from the courtroom as evidence. Rather, they're not regarded as credible evidence, i.e., a polygraph examiner is not treated as an expert witness in regards to the matters of the diagnostics of truth telling. Interestingly, polygraphs can and often are used as evidence in grand jury considerations regarding possible indictments.
Where polygraphs truly have been barred is in the employee screening process for most industries/private firms. This was done by an act of congress in the late 1980's ( Employee Polygraph Protection Act of 1988). Of course, the government excluded itself from such prohibitions.
-tcp
Re:Dangerous stuff (Score:1)
I just rechecked re admissibility and am unhappy to see that in the last few years federal courts are reconsidering the per se exclusion of polygraph tests, largely because of a Supreme Court case called Daubert. States have a variety of rules, most very hostile to polygraph.
I didn't know about the Act -- thanks (I see that it has other exceptions [polygraph.org]). There has been a lot written about the increasing use of the polygraph as a gov't screening measure, despite its multiple failures. I'm concerned that little effort seems to be going into measures that really do advance security.
Re:Dangerous stuff (Score:2)
This may or may not be true in the United States. I suspect that it varies by state.
I know that in Canada they are unequivocally inadmissible in court proceedings. Many other nations have similar policies. Remember, /. readers come from many different jurisdictions.
"Tell me about CowboyNeal" (Score:4, Funny)
Me: CowboyNeal,
It was for charity! (Score:1)
It isn't that great at all (Score:4, Insightful)
Used at an airport: 50000people/day * 28.57% false positives = a lot of messed up flights.
Maybe after they get to better than 99% will it really be useful.
Re:It isn't that great at all (Score:2)
Try to be consistent in your own post!
"it missed 2/7 lies"
"..false positives"
missing a lie is a false negative, and hence would not incur any messed up flights. (If by messed up flight you mean delay, as opposed to blown up by terrorists)
From the (few) tests reported in the article, they have a false positive rate of ZERO.
Re:It isn't that great at all (Score:2)
Errr - typed it after a big lunch with blood suger dropping...
Of course, 7 lies isn't a large enough sample size to be useful anyway, come to think of it. But it still indicates to me that the technology is nowhere near what the article hyped it to be.
Re:It isn't that great at all (Score:1)
Scary (Score:2, Interesting)
Now this thing is very easy to use and operate (contrary to other known methods). And will probably cost peanuts. Which means with 87% accuracy 13% of people who are honest and good citizens will be denied loans, insurances, jobs, etc.
That's more than 1 in 10. Scary, huh?
But how this ends is easy to predict - through generations of breeding more successful people at looking thruthful will prevail and the indifferent faced bustards will perish in extinction.
*makes an honest face*
Is it too late? (Score:2, Funny)
Or maybe they could just apply it during a replay.
VK? (Score:3, Interesting)
"Reaction time is a factor in this, so please pay attention."
I'm not a replicant, but after that movie, I'd still run if I heard that phrase. It's like Heisenberg's Uncertainty Principle. The test dealing with my response will, in turn, affect my response. That's what polygraphs base themselves on, that if you lie, it'll detect your nervousness due to the fact that the test looks "real"
100% foolproof lie detecting program (Score:2)
#include
void main()
{
printf("You're lying!\n");
return;
}
See? Anytime someone lies, this program will tell you so!
Why it doesn't work (Score:1)
Anytime someone lies, this program will tell you so!
But your program has too many false positives. Thus, it's not 100 percent accurate as you suggest.
Re:hmm... (Score:1)
The Lie behind the Lie detector (Score:5, Informative)
Re:The Lie behind the Lie detector (Score:3, Informative)
What happens if... (Score:1)
I've almost done (Score:3, Funny)
Later I found that if I inverse-proportioned the intensity of electric shock to the confidence reading of the lie detector the accuracy would sky-rocket.
Unfortunately, my research was called to stop when a prof. used an obvious lie on my prototype. The confidence level reach 0 and the detector output maximum electric shock which knocked the prof. 10 feets away from the desk.
Damn. it was that tyrannic dictatorship destroyed a great research like that!
Oh boy! More pseudo-science! (Score:4, Insightful)
"Plans are being drawn up to test the machine as part of airport security. Dr Bandar says that by asking passengers simple questions on arrival, customs officers would be able to determine who to search for drugs or other items of contraband."
"The research team have secured a patent application for the system, which they say could bring in billions of pounds for the university and the scientists involved."
Pathetic.
Re:Oh boy! More pseudo-science! (Score:4, Interesting)
Recently, however, there was a committee put together by the National Academy of Sciences to study the scientific validity of the polygraph and related lie-detection methodologies, both in the lab and out in the real world. If you want to read the report, you can find it online [nap.edu] through the NAS's publishing website.
As for what the report says about micro-expressions (from page 164), it notes that previous studies of micro-expression detection were able to achieve rates of up to 75% accuracy, far better than chance. It goes on to note that such methods, at the time of the report's writing, were labor intensive but that recent work in automating the process held promise. It seems that this new AI work is showing that promise to be well founded.
While 75% accuracy is good, it is nowhere near what would be needed in a diagnostic tool. Even 95% accuracy isn't good. (Note, according to signal detection theory, we really should be talking about percentages of false positives and false negatives, but I digress; let's assume the accuracy works the same for both error types.) 95% accuracy would mean that for every 100 truthful people interviewed, 5 would be judged as liars. For every 1,000 people, 50. Inasmuch as such false positives can ruin lives, careers, marriages, reputations, etc., that rate is too high. Likewise, if 5 out of 100 liars slip through, that isn't a test I feel confident using for national security concerns. Even "good science" needs to be damned good to fill the shoes made for the "lie-detector".
-tcp
Uhh.. (Score:2, Funny)
I know how to defeat it. (Score:1)
hypnosis (Score:1)
Top 10 uses for this new technology! (Score:2)
10. Asking Ken Lay if he knew about the rampant fraud at Enron and Arthur Anderson and CitiGroup's complicity.
9. Asking Dick Cheney if he knew about the Enron/Dynergy price-fixing during California's 2000 energy crisis.
8. Asking Dubya about his Air National Guard appointment and discharge.
7. Asking Dubya about the profit made on the sale of the Rangers.
6. Asking Dubya about his late Harken stock sale report form to the SEC.
5. Asking Dubya about his DUIs.
4. Asking Dubya about proof of Saddam's WOMD program.
3. Asking Bill Gates about Microsoft's intentions for Palladium.
2. Asking Hillary Rosen about her close physical relationship with Satan.
1. Asking Trent Lott about his actual intent in stating his support for Thurmond's presidential candidacy.
TIE
1. Asking King Faisal about House of Saud's covert support for Al Qaida.
Ooh, I'm sorry, did I do that? here, let me clean that up. . . .
Paralyze those muscles (Score:2)
Not for canada (Score:1)
Tisk tisk... (Score:2)
ie. their lack of it.
Read the story, watch the movie.
87% Accurate, Eh? (Score:2)