Download - University of Calgary

builderanthologyΤεχνίτη Νοημοσύνη και Ρομποτική

19 Οκτ 2013 (πριν από 3 χρόνια και 7 μήνες)

80 εμφανίσεις

Marina Gavrilova

Scientific question:


If a person's photo in the system's database was taken 10 years ago, is it
possible to

identify the person today?


Answer can be provided by next generation face reconstruction engines.




3

Fusion



Biometric Fusion

means integration of



biometric information.




The goal of fusion scheme is to devise an appropriate


function that can optimally combine the information


rendered by the biometric subsystems.




Broadly classified as





Prior
-
to
-
matching fusion

and


After
-
matching fusion

Humanoid robots are anthropomorphic robots (have human
-
like
shape)

that include also human
-
like behavioral traits. The field of
humanoid

robotics includes various challenging direct and inverse
biometrics.


On the other hand, in relation to inverse biometrics, robots
attempt

to generate postures, poses, face expressions to better
communicate

their human masters (or to each other) the internal states [49]).

Robots such as Kismet express calm, interest, disgust, happiness,

surprise, etc (see (MIT projects).


More advanced aspects include dialogue and logical reasoning
similar to those of humans. As more robots would enter our
society it will become useful to distinguish them among each
other by robotic biometrics.



7

More advanced aspects
include dialogue and

logical reasoning similar to
those of humans.


As more robots would enter
our society it will become
useful to distinguish them
among each other by robotic
biometrics.


Asimo

(Honda) humanoid
robot


http://en.wikipedia.org/wiki/
ASIMO


17

18


Email


Changed the way we communicate in today’s highly
technical world


What's wrong with the app of the Internet?


Hard to know who sent an email


Spam


Unsolicited email


Offensive


Fraudulent (phishing)


Malicious (viruses, worms, spyware, exploits, DoS)


19

Email
(E)

Signing Algorithm

Private key
D

Signature
(D(H(E)))

Public key
E

If
H`(E) = H(E)
then message is authentic

E

Hash
H

(MD5, SHA
-
1, etc)

D(H(E))

Hash
H

H`(E)

H(E)

20


PEM (Privacy Enhanced Mail) [3]


mid 1980


ASCII email messages


No centralized public key directory


Single root to issue CAs (Certificate Authority)


S/MIME (Secure Multipurpose Internet Mail
Extension) [4]



Accommodate any number of trusted CAs


PGP (Pretty Good Privacy) [5]


Web of trust


Widely used


21


Garfinkel [6] presented a new approach to
solve most of the usability issues


Used only for encryption


Outgoing email


Looks up users public keys in a local database


Appends the user’s public key to the email header


Incoming email


Stores public keys found in the email header


Vulnerable to man
-
in
-
the
-
middle attacks

22


Brown and Snow [7] presented a similar
approach but adds digital signatures


Proxy
-
based approach sitting between the
mail client and mail server


Encrypts and signs all outgoing emails


Decrypts and verifies all incoming emails


23


Idea


Use fingerprints instead of private keys


Primary goals


Secure access to email accounts


Provide an easier way to sign and verify emails


Solve the usability issues


Implemented as an email client called SEFR


SEFR asks you to present your fingerprint


When you access it and try to view your inbox


When you try to send an email

24


Components


Database: used to store user’s fingerprints and
account information


dbs2.cpsc.ucalgary.ca


Enroller: used to enroll new users


Receiver: used to download the user’s inbox


Using POP (Post Office Protocol) [1]


Gmail’s POP server


pop.gmail.com


Port 995


Sender:

used to send emails


Using SMTP (Simple Mail Transfer Protocol) [2]


Gmail’s SMTP server


smtp.gmail.com


Port 465


25


Accounts on Gmail


Two accounts were created for testing and
experimentation purposes


amaobied


sefr.obied


Issues


Gmail servers requires the use of SSL


OpenSSL


Base 64 encoding


Fingerprint scanner in the BT lab


No API


Used fingerprint image paths

26


Signing messages


When a user tries to send an email, SEFR asks the
user to present his/her fingerprint. If the fingerprint
is stored in the database, SEFR does the following:


Transforms the email message (e.g., get rid of
newlines, tabs, spaces, etc)


Create a hash using SHA
-
1 of the transformed
message


Store the sender’s email address, receiver’s email
address and hash in the database




27


Verifying messages


When SEFR tries to verify an email, SEFR
automatically does the following:


Transforms the messages (e.g., get rid of newlines,
tabs, spaces, etc)


Creates a hash using SHA
-
1 of the transformed
message


Extracts the sender’s email address, receiver’s email
address from the email header


Checks if the sender’s email address is associated with
the receiver’s email address and hash value in the
database






28


Using biometric authentication to access
Web
-
based system


Online banking


Defeating Spam


Bill Gates said “Two years from now, spam will be
solved”





The issue of protecting privacy in biometric systems has
inspired the area of so
-
called cancelable biometrics. It
was first initiated by The Exploratory Computer Vision
Group at IBM T.J. Watson Research Center and published
in [2].


Cancelable biometrics aim to enhance the security and
privacy of biometric authentication through generation of
“deformed“ biometric data, i.e. synthetic biometrics.


Instead of using a true object (finger, face), the

fingerprint or face image is intentionally distorted in a
repeatable manner, and this new print or image is used.


30

The features of the new generation of lie detectors include:


(a) Architectural characteristics (highly parallel configuration),

(b) Artificial intelligence support of decision making, and

(c) New paradigms (non
-
contact testing scenario, controlled
dialogue


scenarios, flexible source use, and the possibility of interaction
through an artificial intelligence supported machine
-
human
interface).



38

The idea of modeling biometric data for decision making
support

enhancement at checkpoints is explored, in particular, at the

Biometric Technologies Laboratory at the University of Calgary

(
http://enel.btlab.ucalgary.ca
).


Simulators of biometric data are emerging technologies for

educational and training purposes (immigration control,
banking

service, police, justice, etc.). They emphasize decision
-
making
skills

in non
-
standard and extreme situations.



39