Slashdot Mirror
Computer Models Find Patterns In Asymmetric Threats
The Narrative Fallacy brings us a story about a project by University of Alabama researchers to develop a database capable of anticipating targets for future guerrilla attacks. Quoting Space War:
"Adversaries the US currently faces in Iraq rely on surprise and apparent randomness to compensate for their lack of organization, technology, and firepower. 'One way to combat these attacks is to identify trends in the attackers' methods, then use those trends to predict their future actions,' said UA-Huntsville researcher Wes Colley. 'Some trends from these attacks show important day-to-day correlations. If we can draw inferences from those correlations, then we may be able to save lives by heightening awareness of possible events or changing the allocation of our security assets to provide more protection.' Researchers reviewed the behavior signatures of terrorists on 12,000 attacks between 2003 and mid-2007 to calculate relative probabilities of future attacks on various target types."
It's all part of game theory. If your enemy doesn't randomize their tactics, then you can take advantage of any statistical bias or pattern. Soon anyone buying a geiger counter, thermal noise diode, or even a lava lamp, will be a candidate for the terrorist watch list.
FTA
"This study considered two aspects of each attack: the target of the attack, and the time of the attack. Using careful statistical techniques, the team identified correlations between attacks on various target types as a function of time. For instance, if there were an attack on a government target, that somewhat increased the chance of an attack on a police target over the next several days."
Sounds pretty strait forward. If you have a brazen attack against, say, a base, you can expect a higher risk of attacks on other assets. Isn't that why after the 911 attacks there were Combat Air Patrol flights over every major city for days. This is just common sense...
I've read Slashdot for the last 5 years, and now I start posting... Go figure
Computer models are only as good as their data: Garbage In, Gospel Out. That's a problem with climate modelling. The climatologists keep tweaking the models until they get what they expect and are then smug because the models "prove" their predictions.
If terrorist activity is truely random, then this thing does not stand a chance. However, terrorists, like most people, likely follow some sort of pattern and if the signature "tell tale signs" can really be detected then perhaps attacks etc can be predicted.
Engineering is the art of compromise.
It isn't whether it is an optimal strategy, but whether these tools improve materially the effectiveness of intelligence. "Discovery" AI/Expert systems were finding new materials processes during the 1980s.
Oh ye of little faith. Still, trust in god but lock your car.
Verizon: Latin for "poor rural service".
Supposedly one of the better spies (I forget which) always carried a coin in his pocket that he'd flip every few minutes to make random decisions (get to a street corner: turn or go straight? Flip).
Engineering is the art of compromise.
Either they've found some hidden predictor of attacks, or maybe someone needs a course in basic Ramsey theory [wikipedia.org], which deals with conditions under which order (patterns) must occur even in random noise.
Sure, that's why you have test sets to determine if the models the system learns from the data are useful or not. I think it's safe to assume that the scientists working on this are familiar with the basics of learning theory and modeling.
Just how easy is it to think of something truly random? Ask 100 people to pick a random number between 1 and 10 and you will see a pattern. It won't be random because certain numbers will be preferred. Try asking the person to repeatedly pick a random number between 1 and 10 and they won't be able to do it. Throw in other factors they need to consider and being random gets really hard. By using computer pattern matching we have a shot at discovering patterns they don't even know they have, and perhaps patterns psychologists aren't aware of either. The psychologist will make assumptions, and those assumptions might be wrong or limiting. The computer can think outside the human box. It might just find the pattern without being hampered by questions about why the pattern is there.
I often don't like the choices people make, but I like the fact that people make choices. That's why I'm a conservative.
Really, though, you think they're studying shopping mall attacks? They studied "12,000 terrorist attacks". Bet you didn't know there had been 12,000 terrorist attacks in Iraq in the past four years, did you, let alone 12,000 well documented enough to study? Assuming an average of 20 people killed per attack, that'd mean ~250k people had been killed in well-documented terrorist attacks without the media catching on to the overwhelming majority of it. With that many people being killed by terrorists, who needs insurgents?
Here's a wild notion: they're doing what the US government usually does and calling any insurgent attack a "terrorist attack". Which is why this research is being carried out for the DoD instead of the Department of Homeland Security.
"Is Donald Trump a racist? I'll let you decide 'Yes' for yourself."
Before you rush to judgement, I suggest you play a few rounds of rock, paper, scissors. There's nothing crazy about spending money trying to find patterns in the enemy's behavior, even if he's intentionally trying to be random... that's the entire field of cryptology!
Maybe you haven't been keeping up with things, but the Iraqis are actually taking their country back from the insurgents/terrorists now, with US help in training their army and police. While there are still some bad spots - Al Qaeda moved to Mosul after Baghdad started getting too tough for them - things are enormously better in Iraq now. Iraqis who have day-to-day contact with US forces (and a lot of them do) have a very positive image of our troops, often trusting them to get things done because the Iraqi forces are still dealing with internal bureaucracy and corruption. That word has spread, to the point where people across Iraq are standing up to make their neighborhoods more secure.
This isn't about a simplistic "the trrrists will win if we leave", even though it's true that they will. It's about people's lives. While we shouldn't have gone into Iraq in the first place, it's too late to pretend we never went - we have to deal with the consequences of the invasion and as well as the years during which the "do more for less" policy was pushed by Rumsfeld. Yes, thousands of innocent civilians have died at our hands, and tens of thousands have died at the hands of the terrorists, but hundreds of thousands will die if we leave Iraq to be split up by Iran and Al Qaeda.
By the way, the article wasn't merely talking about preventing attacks on our troops. Part of the surge strategy was to ensure that American troops are in the neighborhoods and interacting with the Iraqi people on a constant basis rather than holing up in bases and bunkers. That opens them up to further attacks, but our troops know how to defend themselves (easily the deadliest thing for our soldiers in a combat situation is buried IEDs, because insurgents and terrorists are usually extremely poor shots using the fairly inaccurate AK-47). What kills so many civilians is suicide bombings, shootings in crowds, and other activities that the study from the article hopes to pattern and predict. Much like the current mission in Iraq, the study is about saving civilian lives first and foremost.
Significance only makes sense when the underlying distribution is known, such as the random sequence I listed as an example. When you have no clue what the underlying distribution is, and can NOT safely assume near-normality because of the central limit theorem, all bets are off. I just don't buy that the distribution of terrorist attacks is normal or even near-normal, not without some hard evidence.
An old-timer with old-timey ideas.
counterintelligence realized most people do not flip when crossing the street.
No, I'm joking. Seriously though, one of the things the military does in Iraq when looking for the foreign jihadis is they watch for wrong turns off main thoroughfares. It is apparently pretty effective at sorting out people who aren't from around here -- if you know Main Street less well than the Americans, you just might be from out of town!
Help poke pirates in the eyepatch, arr.