Biometrics research need for large biometrics identification systems - identity assertion, identity services in the cloud

1. Biometrics As an Enabling Technology – Identity Assertion
Entitlement(s)
Actions
Identity
Trust
(Rules)
Status
(Environment)
Establish
Identity
Manage
Identity
Reputation
(History)
© 2014 1 IBM Corporation

2. Different Perspective – Emerging Trends
Data Explosion – more sensors,
proliferation of data collection
Cloud Technology – more mature
Computer Resources – a commodity
• Big Appliances – commodity platforms and
services
• Network, platform, application services
become commodity – same for biometrics
Analytics Tools – readily available
Open Source – simply proliferated
Standard Adoption – NIST-ITL, INCITS
and many others
Low Government Funding – mega
programs (NGI, US-VISIT, UUID) don’t
come often, ST fund reducing
© 2014 2 IBM Corporation

3. A Need – Establish Identity Service in the Cloud
Focus on Identity Assertion
• Biometrics as an enabling technology
• Avoid a race for accuracy
• Business owners have limited resources for better sensors, more data and etc.
• Business owners still want the same performance with a smaller budget
Driven by Economics and Technology Trends
• Proliferation of data collection and mobility
• Success or advancement of Big Data infrastructureand platform technologies
• Advancement of IT industry and commoditization
• Leverage all data sources available and within the “vicinity”
Areas of Challenges
• Security, privacy, and protection for cloud based identity
information
• Secure biometrics data
• Techniques to address privacy
• Contextual information fusion through context accumulation
• Research spatial temporal impact
• Bringing identity resolution technologies into the mix
• Other information including biographic
© 2014 3 IBM Corporation

4. A Challenge – Working with Low Quality Data
“A fact of life”
• Low Resolution Data
• Out of Focus Image
• Unconstrained Capture
• Insufficient Color/Grayscale
Information
• Limited Data Samples
• Many more
© 2014 4 IBM Corporation

5. Dr. Charles Li
Technology and Strategy
IBM Federal CTO Group
Charles_li@us.ibm.com
202 330 109
© 2014 5 IBM Corporation

6. Perceptions on biometrics
technology and system
What is missing?
© 2014 6 IBM Corporation

7. Biometrics Data at Scale – Static Single Instance
ID Cards/Border Crossings/Benefits/Multiple
Instances
7,000,000,000x(10 Print 0.5-1MB + Face 200KB +
IRIS KB)
7 Exabytes
Prolific Usage of Mobile Phones
6 Billion Mobile Phones
6 Exabytes of behavior data
1 Billion Arrivals 2012 world wide
United States – 100-200 million
international arrivals 2012
1 Exabytes traveling data
Unique Identification Authority of India (UIDAI)
plans to enroll 1.2 billion citizens.(UID
Program) ( enroll million /day; half billion by
2014) 3-4 Exabytes Biometrics
Biographic Data
DHS IDENT over 150 million
identities;
125,000 transactions daily
~100-300 Terabytes
1 GigaBytes = 1000MB
1 TeraBytes = 1000GB
1 PetaBytes = 1000TB
1 ExaByes = 1000PB
1 ZettaBytes = 1000EB
1 YottaBytes = 1000ZB
FBI NGI ~ over100 Million
Fingerprints More coming plus
Faces/Iris
~100-200 Terabytes
US DoS has in the range of
100 million faces Others
~ at least 10-50 Terabytes
EU VIS Biometrics Matching System (BMS) at
70 million individuals and 100K daily enrollment
~100 Terabyte
many instances, history, transaction, logs… data in reality
© 2014 7 IBM Corporation

8. Other Big data examples
By 2016, annual Internet traffic
will reach 1.3 Zettabytes
Facebook processes
500+ Terabytes of data daily
150 Exabytes global size of
“Big Data” in Healthcare, growing
between 1.2 and 2.4 EX / year
Google processes
24 Petabytes
of data in a single day
Twitter processes
12 Terabytes of data daily
ATT transfers about
30 Petabytes of data through
its network daily
We don’t have the most challenging problem!
For every session, NY Stock
Exchange captures 1 Terabyte
of trade information
Hadron Collider at CERN
generates 40 Terabytes
of usable data / day
© 2014 8 IBM Corporation

9. Biometrics Identity Cloud
Services
Field Operation
© 2013 IBM Corporation
Biometrics Identity Service Cloud Model
Operational Cloud
Biometrics as a Service
Adjust resources based on load
Biometrics
Data Sources
Facial
Elastic Compute
Resources
… Finger
print
Biometric
and
Identity
Services
Develop/Test Cloud
Test Bed
Test
Data
Compute
Resources
Data
Service
and
algorithm
Dev/Test
Mobile clients
User
User
User
User
Application/Integration
Services
Web 2.0
Pattern
Data in Motion –
Streaming Pattern
J2EE/OLTP
Patterns
Map/Reduce
Pattern
Mobile
Desktop,
Interoperate
Analyst – Human
Examiner
• Cloud – Data, Compute, Network
• Options – On-premise, Off-
Premise, Hybrid
• Enroll, Identity, Identity, Retrieve,
• Subject Manipulation(create, delete,
update, retrieve),
• Biometrics and Biographic manipulation
1
4
3
2
5