CAPTCHA

1
CAPTCHA THE ESP GAMESHAH JAYESH
CS575 SPRING 2008
2
OVERVIEW

• What is CAPTCHA?
• Examples.
• Applications.
• How to Beat CAPTCHA?
• 3-D CAPTCHA.
• The ESP Game.
• Why it is So popular????
• Fact about the ESP Game.
• Questionnaires ??????????

3
(No Transcript)
4
CAPTCHA
A program that can tell whether its user is a
human or a computer.
5
CAPTCHA
"Completely Automated Public (ALL CODE AND
DATA USED BY A CAPTCHA SHOULD BE PUBLICLY
AVAILABLE) Turing Test to tell Computers and
Humans Apart", trademarked by Carnegie Mellon
University.
6
CAPTCHA

• A PROGRAM THAT CAN GENERATE AND GRADE TESTS THAT
• Most Human can pass.
• Current Computer Programs cannot Pass.

7
CAPTCHA

• Also Described as a reverse Turing test,
• It is administered by a machine and targeted to
  a human.
• Contrast to the standard Turing test that is
  typically administered by a human and targeted
  to a machine

The Turing test is a proposal for a test of a
machine's capability to demonstrate intelligence.
8
HISTORY
The potential difficulty of differentiating
humans from computers pretending to be humans was
addressed at least as early as 1950, when Alan
Turing described his now-famous Turing test.
Automated tests which distinguish humans from
computers for the purpose of controlling access
to web services were first discussed in 1996.
Primitive CAPTCHAs seem to have been developed
in 1997 at AltaVista by Andrei Broder and his
colleagues to prevent bots from adding URLs to
their search engine. In order to make the images
resistant to OCR (Optical Character Recognition),
the team simulated situations that scanner
manuals claimed resulted in bad OCR. In 2000,
Luis von Ahn and Manuel Blum developed and
publicized the notion of a CAPTCHA, which
included any program that can distinguish humans
from computers. They invented multiple examples
of CAPTCHAs, including the first CAPTCHAs to be
widely used, which were those adopted by
Yahoo!. The term "CAPTCHA" was coined in 2000 by
Luis von Ahn, Manuel Blum, Nicholas J. Hopper
(all of Carnegie Mellon University), and John
Langford (then of IBM).
9
EXAMPLE

• Picks Random Renders it into a
• String of Letters. Distorted Image.

• following finding

10
and Generates a TESTType the Characters
that Appear in the Image.
11
APPLICATIONS

• To Stop Spammers.
• Stopping automated posting to blogs, forums and
  wikis.
• To Protect systems vulnerable to e-mail spam,
  such as webmail services of Gmail, Hotmail, and
  Yahoo! Mail.

12
EXAMPLES OF CAPTCHA

http//www.alipr.com/captcha/
13
EXAMPLES OF CAPTCHA

What are this Images of ????????
14
EXAMPLES OF CAPTCHA

The Images need to be randomly distorted ..
15
EXAMPLES OF CAPTCHA

What are these Pictures of ????????
16
SOUND BASED CAPTCHA

• Humans are better than Computers
  at understanding of spoken Languages.

17
How to beat CAPTCHA?

• Extraction of the image from the web page.
• Removal of background clutter.
• Segmentation.
• Identifying the letter for each region.

18

• Steps 1, 2, and 4 are easy tasks for
  computers. The only part where humans still
  outperform computers is segmentation.
• The segmentation becomes nearly impossible with
  current software. Hence, an effective CAPTCHA
  should focus on the segmentation.

19
THE 3-D CAPTCHA

• The 3-D CAPTCHA and modern video games use the
  same basic mechanism to generate unique images.
• A single 3-D CAPTCHA image might contain 26
  identifiable features and asking for the
  identification of 3 of those features will
  result in (26)(25)(24) 15,600 possible
  combinations while the requirement to identify
  5 features will result in 7,893,600 combinations
  making a brute force attack impractical.

20
THE 3-D CAPTCHA

• Designing a computer vision program that can
  recognize the objects within the 3-D CAPTCHA
  images is intrinsically difficult.
• The instructions that accompany the 3-D CAPTCHA
  image are bound by language dependency. Any
  entity deploying the 3-D CAPTCHA will need to
  select the language to be used for the
  instructions that will accompany the image.

21
EXAMPLE OF 3-D CAPTCHA

We now have the code CKT
22
DIRTY HACKS
CAPTCHA sweat shops SPAM COMPANIES HIRE HUMANS
TO SOLVE CAPTCHAS ALL DAY LONG 2.50 PER HOUR
FOR EACH HUMAN 720 CAPTCHAS PER HOUR PER
HUMAN 1/3 CENT PER ACCOUNT.

23
(No Transcript)
24
The ESP Game

25
The ESP Game
Labeling Images with Words Man Ho
rse Ground Belly Still an open
problem
26
ACCESSIBLITY
Less than 10 of the web is accessible to the
visually impaired. Reason Most images dont
have proper Captions.
27
The ESP Game

• Two Player online Game.
• Partners dont know each other and cant
  communicate.
• Objective of Game
• Type the Same Word.
• The only thing in common is an Image.

28
THE ESP GAME
PLAYER 1 PLAYER 2
29
The ESP Gamehttp//www.espgame.org/
30
FACT

• THE ESP Game is Fun !!!!!!!
• 4.1 million labels with 23,000 players.
• There are many people that play over 20 hours
  a week.
• 5000 people playing simultaneously can label
  all images on Google in 30 days!
• Individual games in yahoo! And msn average over
  5,000 players at a time.

31
WHY DO PEOPLE LIKE THE ESP GAME?
32

• The ESP Game gives its players a weird and
  Beautiful sense of anonymous intimacy.
• On the other hand, the two of you are bringing
  your minds together in a way that lovers would
  envy.

33

• Strangely Addictive.
• Its so much fun trying to guess what others
  think. You have to step outside of yourself to
  match.
• Its fast-paced.
• Helps me learn English.

34
THE POWER OF HUMAN CYCLES
CAPTCHA
OPEN PROBLEM
GAME
35
HAS APPEARED IN OVER 50 NEWSPAPERS AROUND
THE WORLD.
THE ESP GAME
36
(No Transcript)
37
Name That Image Computers excel at sifting
information, but they have trouble distinguishing
a picture of a tree from one of a turtle. So
researchers at Carnegie Mellon University knew
they needed human volunteers to successfully
label millions of unmarked images on the Web.
Luis von Han, a graduate student in computer
science, had the inspired idea of turning the
laborious process into a two-player contest
called the ESP Game Each time you play, you
are randomly paired with another anonymous
player. You can't communicate with your partner,
although you both see the same image. The goal is
to guess the descriptive word your partner is
typing for the image. Once you both type the same
word, you see a new image. Since October the
game has attracted 15,000 registered players, and
they have created more than 1.5 million labels (a
label is a single descriptive word most photos
require multiple labels). The site draws from a
database of 200,000 Web images another 200,000
are to be added soon. Mr. von Han said that
properly labeling Web images would allow for more
efficient image searching, improve the screen
readers used by the visually impaired and help
users block inappropriate images.
38
(No Transcript)
39
REFERENCES

• http//en.wikipedia.org/wiki/Captcha
• http//www.espgame.org/
• http//www.captcha.net/
• http//www.alipr.com/captcha/

40
THANK YOU NO QUESTIONS ??????