Upload
abigail-hodge
View
213
Download
0
Embed Size (px)
Citation preview
Model Building for EnhancingHomeland Security
James R. ThompsonDept. of StatisticsRice University
Supported in part by the Army Research Office (Durham) underDAAD19-99-1-0150.
Some Useful TextsHerman Kahn On Thermonuclear WarThinking About the Unthinkable On Escalation
Victor Hanson Carnage and Culture
James Thompson Simulation: A Modeler’s Approach
James Thompson & Jacek KoronackiStatistical Process Control: the Deming ParadigmAnd Beyond
Deming’s Theorem for AcceptanceSampling
Under the Risk Function of ExpectedValue, the Number of Sampled ItemsShould be Zero or the Number in theTotal Sample.
Let Q be the total expected cost involved in sampling of a batch of nLet x be the number of items inspectedLet c1 be the cost of examining an item,Let c2 be the cost of accepting a bad itemLet p be the probability an item is defective
Q= c1 x + (n-x)p c2
=(c1 - p c2 )x+ n p c2.
Then it is clear that we minimize Q by If c1 > pc2, set x=0; If c1 <pc2, set x=n.
Unfortunately, The Cost of Missing A Terrorist Is SoHigh That Deming’s Theorem Tells Us To SubjectAll Passengers To A Thorough Inspection.
Problem: If We Did This, We Would Bankrupt The US Airline Industry.
Reality: We Have To Work With A Constrained OptimizationProblem.
Our Task: With x and n Fixed, Find the Allocation of Thorough Samplings Which Minimizes Q.
n = n1+n2
Assume second population more likely to exhibit "failures"
Q= c0 x 1 + (n1 - x1 ) p1 c + c0 x2 +(n2 - x2) p2 c
Q=x 1 (c0 - p1 c ) + n1 p1 c + x2 (c0 - p2 c ) + n2 p2 c .
Most likely, c0 -p2 c <0.
Consequently, since we are limited by inspectionscapacity to inspect a total of x items, we should follow the following rule
If n2 < x, sample all persons from Group 2 and x-n2 persons chosen at random from Group 1.
If n2 > x, sample x persons from Group 2. Consider delaying flight until all n2 are sampled.
Does this mean profiling? Yes. Here is a profiling strategy.
1.Let the first persons checked be the least likely (by stereotype) to be terrorists. Older persons of European origin, may be selectedas frequent victims of the thorough search.
2. Select all persons in the group of particular interest for thorough checking.
Perhaps, all this is illegal. It is certainly profiling.Under the present situation, it appears unlikely thatclass action lawsuits would be filed. There is a certainfalse symmetry presented when nuns and rabbis are being checked, albeit, on the average, much lessfrequently than young Muslim males. It has the effectof being onerous to all groups without singling out one group and excluding others. Because the persons of stereotypical inclusion in the riskier group are inthe small minority, it will almost always be thecase that the middle-aged white businessmen andgrandmothers outnumber young Muslim males astargets of inspection.
Even if the proportionality of inspection be verydifferent among the various groups, as long as allare significantly at risk of being checked, it seemsthat the kind of inspection currently followed will betolerable to all, at least for the foreseeable future.
We note here an obvious strategy for the terrorist game master:flood flights with large numbers of persons from Group 2 so that n2>x.
This can be done for numerous flights over time without anyuntoward items being on the inspected persons. This can disruptthe inspection system.
On the other hand, a sophisticated security game master can then look at putative causes of these pulse floods of persons from Group 2, e.g., travel to conventions, etc., and the identities of the persons from Group 2 in the floods, and backtracking their contacts. The commonality of travel reasons provides a venue for discovering the activity of the terrorist game master. Even if the putative travel reasons are such matters as visiting relatives, goingon holiday, the security game master can seek threads of commonality amongst the travelers as a venue for discovering the activity of the terrorist game master.
At the present time, it is unlikely the linkages betweenal-Quaida and the mainstream American Muslim community aresufficient to provide cascades of suspicious persons to pushthrough the system. However, continuing disaffection due to illtreatment of, say, Palestinians, might, if unchecked, lead to a situation where people who were unwilling tocommit a terrorist act might nonetheless be willing to participate in discomfiting the security system.The current security system of the airlines would be seriously stressed if the mainstream Islamic communitystarted to be so offended by US foreign policy that they,and their friends, spontaneously participatedin a kind of defacilitation of the security system.
Thus, we note another grand strategy possible for the security game master: minimize, by changes in policy, the fraction of persons in the general population who are in Group 2. That might be achieved by foreign policy modifications, such as establishment of a viable Palestinian state.
Negative reinforcement is also a possibility. For example, there appears to be substantial evidence thatWahabi mosques in the United States are established via funds fromthe Saudi state. Since proselytization by nonIslamic groups isstrictly forbidden in Saudi Arabia (as is public Christian worship),the Saudi government might be told to cease such Wahabist supportforthwith. It might also be indicated that the next time an attack organized by Saudi activists took place onNATO territory, occupation of Saudi oil properties would beexecuted forthwith.
This is, of course, a political matter, rather than a statistical one, and the strategies listed in this paragraph are simply hypothetical. However, the posing of the problem in a simple mathematical model at least gives information to policy makers which they may find useful. Diminishing n2 and/or p2 by positive and/or negative reinforcement is clearly indicated to be a good thing by the model. Actually, that is the main message of the model: diminish n2 and/or p2.
For crews, baggage handlers, etc., 100% inspection by regular random polygraphs and inspections whenever entering the work site are clearly in order.
Cost saving technology in the transportation of goods has led to the use of large containers of standarddimensions which can be loaded and stacked in ships andeasily transferred to trucks. The size of thesecontainers is sufficient to accommodate thermonuclear devicesin the multiple-megaton range. Dirty bombswith thousands of pounds of nonfissionable nuclear materialwith a conventional explosive trigger are easy tocontruct and can be accommodated by such containers. Mostof our major ports are within a few miles ofpopulation centers. Rail and truck logistics plus offloading considerations do not admit of taking cargooff in isolated ports. Even were this possible, the containersmight be detonated while on rail lines ortrucks. This kind of Trojan horse strategy for the terrorist gamemaster would appear to be too temptingto resist for long.
Thinking Outside the Box
War is too important to be left to thegenerals. Clemenceau
Homeland Security Is Too ImportantTo Be Left To The Policy Wonks.
President Eisenhower warned of the military industrial complex.
Now we must worry about the cozy relationbetween a host of federal agencies, think tanks,beltway bandits, academia.
Consider the “War on AIDS.”
America has spent more on AIDS than the rest of the First Worldcombined. And it has done the poorest job in the First World of controllingAIDS. The political correctness of the CDC would not allow the simpleexpedient of closing the gay bathhouses in the USA. Thus we have an AIDS rate ten times that in the UK.
If one or more federal agencies want to showthat the “Gulf War Syndrome” is purely delusional, they may be assured of widespreadsupport within think tanks, universities, other federal agencies and professional scientificassociations.
The pervasive spread of federal fundingthroughout American society has broughtthe levels of professional objectivity of scholars and researchers to a level farlower than anything Eisenhower envisioned.We tend to spend far too much time admiringthe Emperor’s new clothes. We are approachingSomething of the scientific era of politicalcorrectness typified in the Soviet Union by thebizarre genetics of Lysenko. We recall that manyof those who disagreed with Lysenko (including histhesis advisor) wound up in the gulags.
Trofim Denisovitch Lysenko (1898-1976)
Herman Kahn 1922-1983
Thinking Outside the Box
1. The Escalation Ladder
2. Scenario Analysis
3. Translation of Military Power into Economic Power
4. Translation of Economic Power into Military Power
5. Distributed Decision Nodes
Some of Kahn’s Insights
It is easier to teach quantitative scientists historyand political science than it is to teach historiansand political scientists quantitative reasoning.
Poorly axiomitized models of real geo-politicalsituations can be attacked by quantitative scientists.
It is generally better to have some criterionfunctions about, rather than simply trying to muddle through.
Some Lessons from the Past
Battle of Vienna Sept 11 1683
The First 9-11
Jan Sobieski
Battle of Vienna Sept. 12, 1683
A Different Kind of War
American Religious Identity Survey of 2001
76.5% Christians1.3% Jews0.5% Muslims
Terrorist Organizations
1. Assassins
2. Mahdists
3. Core and Periphery Model
The Old Man kept at his court such boys of twelve years old as seemed to him destined to become courageous men. When the Old Man sent them into the garden in groups of four, ten or twenty, he gave them hashish to drink. They slept for three days, then they were carried sleeping into the garden where he had them awakened.
When these young men woke, and found themselves in the garden with all these marvelous things, they truly believed themselves to be inparadise. And these damsels were always with them in songs and great entertainments; they received everything they asked for, so that they would never have left that garden of their own will.
And when the Old Man wished to kill someone, he would take him and say: ‘Go and do this thing. I do this because I want to make you return to paradise’. And the assassins go and perform the deed willingly.
— The Adventures of Marco PoloHasan-i Sabbah
The Mahdi
Core and Periphery
Attacker in LAX
Beltway Snipers
FraggingSergeant
Other Ideas from the Past
1. Find centers for retaliation against al-Quaida.
2. Consider the possibility of hostage exchanges to insure treaties are maintained.
What New Stuff Can We Bring To The Table?
Models (lots of them)
Data Based Stressing of Models
Arguments about Models
1. Simulation Models for Bio-Terrorist Attacks.
3. Models Which Take Account of Opportunistic Attacks by Powers Which Are Neither Christian Nor Islamic.
2. Models for International Dynamics Between the Western World and the Islamic World.
4. Models Which Distinguish Between Various “Terrorist” Organization Types.
5. Models Which Visualize A Functioning American Society Dealing With Endemic Terrorism.
6. Models Which Seek To Keep The Endemic From Becoming An Epidemic.
7. Models To Deal With Contamination of Municipal Water Supplies.
8. Models To Deal With EMF Attack.
9. Models To Deal With Internet Sabotage.
Memento Mori
A Model May Be Useful, But It Is Unlikely ToBe Complete.
Organizations Who Are Wedded To GenerationsOf Models Built Upon Unproven Concepts ShouldNot Be Surprised If They Get Into Trouble.
Modelers Who Avoid Data Should Be ThemselvesAvoided.
When All Your Experts Are In Agreement,You Are Probably The Victim Of HavingAllowed Funding To Create Orthodoxy
Let Us Try And Avoid
Clash ofCivilizations
Palestine May Be The Key
Yitzhak Rabin 1922-1995 represented theposition that an Israeli state could live inpeace with a Palestinian state on the WestBank and Gaza. He was assassinated by aright wing Israeli.
Jenin after Sharon’s “Pacification”
The traditional position of the Likudis that the boundaries of the “Kingdomof David” must be achieved by Israel.If this model be followed, an extendedwar with Islam is likely. In such a case,America would be drawn in on Israel’s side.This could lead to a perpetual terrorist threatagainst the American homeland.
You shall not molest or oppress an alien, for youwere once aliens yourselves in the land of Egypt.
Exodus 22:20
The Challenges
1. Solve the easy well-posed problems (such as airline inspection) immediately.
2. Begin hard thinking on the harder problems,such as container inspection.
3. Invite outside the box analysis which produces a variety of strategies, rather than one orthodox one.
4. Avoid an unnecessary “Clash of Civilizations.”