social network analysis for homeland security
TRANSCRIPT
-
8/13/2019 Social Network Analysis for Homeland Security
1/16
Social Network Analysis for
National Security
Michael Last
-
8/13/2019 Social Network Analysis for Homeland Security
2/16
Report Documentation PageForm Approved
OMB No. 0704-0188
Public reporting burden for the collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and
maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information,
including suggestions for reducing this burden, to Washington Headquarters Services, Directorate for Information Operations and Reports, 1215 Jefferson Davis Highway, Suite 1204, ArlingtonVA 22202-4302. Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to a penalty for failing t o comply with a collection of information if it
does not display a currently valid OMB control number.
1. REPORT DATE
MAY 20082. REPORT TYPE
3. DATES COVERED
00-00-2008 to 00-00-2008
4. TITLE AND SUBTITLE
Social Network Analysis for National Security
5a. CONTRACT NUMBER
5b. GRANT NUMBER
5c. PROGRAM ELEMENT NUMBER
6. AUTHOR(S) 5d. PROJECT NUMBER
5e. TASK NUMBER
5f. WORK UNIT NUMBER
7. PERFORMING ORGANIZATION NAME(S) AND ADDRESS(ES)
Department of Defense,Washington,DC,20301
8. PERFORMING ORGANIZATION
REPORT NUMBER
9. SPONSORING/MONITORING AGENCY NAME(S) AND ADDRESS(ES) 10. SPONSOR/MONITORS ACRONYM(S)
11. SPONSOR/MONITORS REPORT
NUMBER(S)
12. DISTRIBUTION/AVAILABILITY STATEMENT
Approved for public release; distribution unlimited
13. SUPPLEMENTARY NOTES
Presented at the 3rd Annual Quantitative Methods in Defense and National Security (QMDNS), May 2008,
Durham, NC
14. ABSTRACT
15. SUBJECT TERMS
16. SECURITY CLASSIFICATION OF: 17. LIMITATION OFABSTRACT
Same as
Report (SAR)
18. NUMBER
OF PAGES
15
19a. NAME OF
RESPONSIBLE PERSONa. REPORT
unclassified
b. ABSTRACT
unclassified
c. THIS PAGE
unclassified
Standard Form 298 (Rev. 8-98)Prescribed by ANSI Std Z39-18
-
8/13/2019 Social Network Analysis for Homeland Security
3/16
COIN o erations re uire assessin the olitical
and social architecture of the operationalenvironment, from both friendly and enemyers ectives. SNA can hel commanders
understand how an insurgent organization
operates. Insurgent networks often do not. ,SNA can help commanders determine what kindof social network an insurgent organization is.
what the network looks like, how it is connected,and how to best defeat it.
-
8/13/2019 Social Network Analysis for Homeland Security
4/16
Social Networks in the US Army/Marine
Requests for research
-
8/13/2019 Social Network Analysis for Homeland Security
5/16
,
Nodes are actors
, ,
NOT Elephants
Bidirectional: A knows B, A communicates with B
Directed: A gives orders to B, A knows of B
Which is A is a friend of B?
-
8/13/2019 Social Network Analysis for Homeland Security
6/16
Proportion of possible edges that exist
Number of shortest paths containing an edge
- -,
Number of neighbors, or connections goingin/out
Other graph measures
# com onents diameter avera e distance
-
8/13/2019 Social Network Analysis for Homeland Security
7/16
-
8/13/2019 Social Network Analysis for Homeland Security
8/16
-
Dense networks are vulnerable network
-
8/13/2019 Social Network Analysis for Homeland Security
9/16
commanders of the 4th Infantry Divisions ent the summer of 2003 buildin linkdiagrams showing everyone related to
Hussein by blood or tribe. Those familyagrams e o e owes eve , u
nonetheless highly trusted, relatives and
helping him move around the
-
8/13/2019 Social Network Analysis for Homeland Security
10/16
Late in the ear a series of o erations
produced an abundance of new intelligenceabout the insurgency and Husseins.
series of raids to capture key individuals and
leaders of the former re ime who could leadcounterinsurgents to him. Each mission gainedadditional information, which shaped the next
Husseins most trusted inner circle and finally toHusseins capture.
-
8/13/2019 Social Network Analysis for Homeland Security
11/16
-
8/13/2019 Social Network Analysis for Homeland Security
12/16
-
8/13/2019 Social Network Analysis for Homeland Security
13/16
SAMSI has looked at this
e w r w ere y e e
Layered networks? Links in orm each other ho do we leverage
this information?
m ar y measures
-
8/13/2019 Social Network Analysis for Homeland Security
14/16
Kinship permanent
Buys from transitory
arac er ze eren e cyc es
Differences between types of links
An instance of an order different from givesorders to
-
8/13/2019 Social Network Analysis for Homeland Security
15/16
-
inference .
How many orders -> Gives orders to?
I task my coworkers. Do I give them orders?
detection from other data sources?
-
8/13/2019 Social Network Analysis for Homeland Security
16/16
Graphs as Statistics
.Statistics on Graphs
urren para gm:
Graph is given
a s cs are unc ons o grap
Draw inference from graph y oug :
Graph summarizes data it is a statistics,
. Functions of graph project to lower
dimensions analo ous to PCA