Transcript Lecture 19 - The University of Texas at Dallas

Data and Applications Security
Developments and Directions
Dr. Bhavani Thuraisingham
The University of Texas at Dallas
Lecture ##9
Data Mining, Security and Privacy
March 21, 2007
Objective of the Unit
 This unit provides an overview of data mining for security (national
security) and then discusses privacy
Data Mining for Counter-terrorism
Data Mining for
Counterterrorism
Data Mining for
Non real-time
Threats:
Gather data,
build terrorist profiles
Mine data,
prune results
Data Mining for
Real-time
Threats:
Gather data in real-time,
build real-time models,
Mine data,
Report results
Data Mining Needs for Counterterrorism:
Non-real-time Data Mining
 Gather data from multiple sources
- Information on terrorist attacks: who, what, where, when, how
- Personal and business data: place of birth, ethnic origin,
religion, education, work history, finances, criminal record,
relatives, friends and associates, travel history, . . .
- Unstructured data: newspaper articles, video clips, speeches,
emails, phone records, . . .
 Integrate the data, build warehouses and federations
 Develop profiles of terrorists, activities/threats
 Mine the data to extract patterns of potential terrorists and predict
future activities and targets
 Find the “needle in the haystack” - suspicious needles?
 Data integrity is important
 Techniques have to SCALE
Data Mining for Non Real-time Threats
Integrate
data
sources
Clean/
modify
data
sources
Build
Profiles
of Terrorists
and Activities
Mine
the
data
Data sources
with information
about terrorists
and terrorist activities
Report
final
results
Examine
results/
Prune
results
Data Mining Needs for Counterterrorism:
Real-time Data Mining
 Nature of data
- Data arriving from sensors and other devices

Continuous data streams
- Breaking news, video releases, satellite images
- Some critical data may also reside in caches
 Rapidly sift through the data and discard unwanted data for later use
and analysis (non-real-time data mining)
 Data mining techniques need to meet timing constraints
 Quality of service (QoS) tradeoffs among timeliness, precision and
accuracy
 Presentation of results, visualization, real-time alerts and triggers
Data Mining for Real-time Threats
Integrate
data
sources in
real-time
Rapidly
sift through
data and
discard
irrelevant
data
Build
real-time
models
Mine
the
data
Data sources
with information
about terrorists
and terrorist activities
Report
final
results
Examine
Results in
Real-time
Data Mining Outcomes and Techniques for
Counter-terrorism
Data Mining
Outcomes and
Techniques
Classification:
Build profiles of
Terrorist and
classify terrorists
Association:
John and James
often seen
together after an
attack
Link Analysis:
Follow chain
from A to B
to C to D
Clustering:
Divide population; People from
country X of a certain religion;
people from Country Y
Interested in airplanes
Anomaly Detection:
John registers at
flight school;
but des not care
about takeoff or
landing
Example Success Story - COPLINK
 COPLINK developed at University of Arizona
- Research transferred to an operational system currently
in use by Law Enforcement Agencies
 What does COPLINK do?
Provides integrated system for law enforcement;
integrating law enforcement databases
- If a crime occurs in one state, this information is linked to
similar cases in other states
It has been stated that the sniper shooting case may have
been solved earlier if COPLINK had been operational at
that time
-
Where are we now?
 We have some tools for
- building data warehouses from structured data
- integrating structured heterogeneous databases
- mining structured data
- forming some links and associations
- information retrieval tools
- image processing and analysis
- pattern recognition
- video information processing
- visualizing data
- managing metadata
What are our challenges?
 Do the tools scale for large heterogeneous databases and petabyte
sized databases?
 Building models in real-time; need training data
 Extracting metadata from unstructured data
 Mining unstructured data
 Extracting useful patterns from knowledge-directed data mining
 Rapidly forming links and associations; get the big picture for real-
time data mining
 Detecting/preventing cyber attacks
 Mining the web
 Evaluating data mining algorithms
 Conducting risks analysis / economic impact
 Building testbeds
IN SUMMARY:
 Data Mining is very useful to solve Security Problems
- Data mining tools could be used to examine audit data
-
-
and flag abnormal behavior
Much recent work in Intrusion detection (unit #18)
 e.g., Neural networks to detect abnormal patterns
Tools are being examined to determine abnormal patterns
for national security
 Classification techniques, Link analysis
Fraud detection
 Credit cards, calling cards, identity theft etc.
BUT CONCERNS FOR PRIVACY
Outline
 Data Mining and Privacy - Review
 Some Aspects of Privacy
 Privacy Preserving Data Mining
 Platform for Privacy Preferences
 Challenges and Discussion
Some Privacy concerns
 Medical and Healthcare
- Employers, marketers, or others knowing of private medical
concerns
 Security
- Allowing access to individual’s travel and spending data
- Allowing access to web surfing behavior
 Marketing, Sales, and Finance
- Allowing access to individual’s purchases
Data Mining as a Threat to Privacy
 Data mining gives us “facts” that are not obvious to human analysts
of the data
 Can general trends across individuals be determined without
revealing information about individuals?
 Possible threats:
Combine collections of data and infer information that is private
 Disease information from prescription data
 Military Action from Pizza delivery to pentagon
 Need to protect the associations and correlations between the data
that are sensitive or private
-
Some Privacy Problems and Potential Solutions
 Problem: Privacy violations that result due to data mining
- Potential solution: Privacy-preserving data mining
 Problem: Privacy violations that result due to the Inference problem
- Inference is the process of deducing sensitive information from
the legitimate responses received to user queries
- Potential solution: Privacy Constraint Processing
 Problem: Privacy violations due to un-encrypted data
- Potential solution: Encryption at different levels
 Problem: Privacy violation due to poor system design
- Potential solution: Develop methodology for designing privacyenhanced systems
Some Directions:
Privacy Preserving Data Mining
 Prevent useful results from mining
- Introduce “cover stories” to give “false” results
- Only make a sample of data available so that an adversary is
unable to come up with useful rules and predictive functions
 Randomization
- Introduce random values into the data and/or results
- Challenge is to introduce random values without significantly
affecting the data mining results
- Give range of values for results instead of exact values
 Secure Multi-party Computation
- Each party knows its own inputs; encryption techniques used to
compute final results
Privacy Preserving Data Mining
Agrawal and Srikant (IBM)
 Value Distortion
- Introduce a value Xi + r instead of Xi where r is a
random value drawn from some distribution
 Uniform, Gaussian
 Quantifying privacy
Introduce a measure based on how closely the
original values of modified attribute can be
estimated
 Challenge is to develop appropriate models
Develop training set based on perturbed data
 Evolved from inference problem in statistical
databases
-
-
Privacy Constraint Processing
 Privacy constraints processing
- Based on prior research in security constraint processing
- Simple Constraint: an attribute of a document is private
- Content-based constraint: If document contains information
about X, then it is private
- Association-based Constraint: Two or more documents taken
together is private; individually each document is public
- Release constraint: After X is released Y becomes private
 Augment a database system with a privacy controller for constraint
processing
Architecture for Privacy
Constraint Processing
User Interface Manager
Privacy
Constraints
Constraint
Manager
Query Processor:
Constraints during
query and release
operations
DBMS
Database Design
Tool
Update
Processor:
Constraints during
database design
operation
Constraints
during update
operation
Database
Semantic Model for Privacy Control
Dark lines/boxes contain
private information
Cancer
Influenza
Has disease
John’s
address
Patient John
address
England
Travels frequently
Data Mining and Privacy: Friends or Foes?
 They are neither friends nor foes
 Need advances in both data mining and privacy
 Need to design flexible systems
- For some applications one may have to focus entirely on “pure”
data mining while for some others there may be a need for
“privacy-preserving” data mining
- Need flexible data mining techniques that can adapt to the
changing environments
 Technologists, legal specialists, social scientists, policy makers and
privacy advocates MUST work together
Platform for Privacy Preferences (P3P):
What is it?
 P3P is an emerging industry standard that enables
web sites t9o express their privacy practices in a
standard format
 The format of the policies can be automatically
retrieved and understood by user agents
 It is a product of W3C; World wide web consortium
www.w3c.org
 Main difference between privacy and security
User is informed of the privacy policies
User is not informed of the security policies
-
Platform for Privacy Preferences (P3P):
Key Points
 When a user enters a web site, the privacy policies
of the web site is conveyed to the user
 If the privacy policies are different from user
preferences, the user is notified
 User can then decide how to proceed
Platform for Privacy Preferences (P3P):
Organizations
 Several major corporations are working on P3P
standards including:
Microsoft
IBM
HP
NEC
Nokia
NCR
 Web sites have also implemented P3P
 Semantic web group has adopted P3P
-
Platform for Privacy Preferences (P3P):
Specifications
 Initial version of P3P used RDF to specify policies
 Recent version has migrated to XML
 P3P Policies use XML with namespaces for
encoding policies
 Example: Catalog shopping
Your name will not be given to a third party but
your purchases will be given to a third party
<POLICIES xmlns =
http://www.w3.org/2002/01/P3Pv1>
<POLICY name = - - - </POLICY>
</POLICIES>
-
Platform for Privacy Preferences (P3P):
Specifications (Concluded)
 P3P has its own statements a d data types
expressed in XML
 P3P schemas utilize XML schemas
 XML is a prerequisite to understanding P3P
 P3P specification released in January 20005 uses
catalog shopping example to explain concepts
 P3P is an International standard and is an ongoing
project
P3P and Legal Issues
 P3P does not replace laws
 P3P work together with the law
 What happens if the web sites do no honor their
P3P policies
Then appropriate legal actions will have to be
taken
 XML is the technology to specify P3P policies
 Policy experts will have to specify the policies
 Technologies will have to develop the
specifications
 Legal experts will have to take actions if the
policies are violated
-
Challenges and Discussion
 Technology alone is not sufficient for privacy
 We need technologists, Policy expert, Legal experts
and Social scientists to work on Privacy
 Some well known people have said ‘Forget about
privacy”
 Should we pursue working on Privacy?
- Interesting research problems
- Interdisciplinary research
- Something is better than nothing
- Try to prevent privacy violations
- If violations occur then prosecute
 Discussion?