[attachment=15338]
Seminar Report onAudio CAPTCHA: Existing solutions assessment and It’s Advancements
What are CAPTCHAs?
Completely Automated Public Test to Tell Computers and Humans Apart.
Web-based protection mechanisms
Only humans allowed to perform certain tasks`
Opening E-mail accounts
Voting on-line, etc.
Prevent automated attacks by bots
To avoid eating up resources
To avoid biasing results, etc.
Most current systems - text-based.
Why there came a need for Captchas???
Preventing Comment Spam in Blogs. 
Protecting Website Registration. 
Protecting Email Addresses From Scrapers. 
Worms and Spam.
Search Engine Bots. 
Preventing Dictionary Attacks. 
Online Polls.
Background
First used by Altavista in1997
Reduced SPAM add-url by over 95%
CMU/Yahoo!
Automated the creating and grading of challenges
PARC
Relies on document image degradation to prevent successful OCR
Conducted user-focused studies to assess the effectiveness of CAPTCHAs
Background - Papers
Pessimal Print: A Reverse Turing TestAllison L. Coates, Henry S. Baird, Richard J. Fateman
Telling Humans and Computer Apart AutomaticallyLuis von Ahn, Manuel Blum, and John Langford
CAPTCHA: Using Hard AI Problems for SecurityLuis von Ahn, Manuel Blum, Nicholas J. Hopper, and John Langford
Using Machine Learning to Break Visual Human Interaction Proofs (HIPs)Kumar Chellapilla, Patrice Y. Simard
Types of CAPTCHAs
Text based
Gimpy, ez-gimpy
Gimpy-r, Google CAPTCHA
Simard’s HIP (MSN)
Graphic based
Bongo
Pix
Audio Based
Text Based CAPTCHAs
Gimpy, ez-gimpy
Pick a word or words from a small dictionary
Distort them and add noise and background
Gimpy-r, Google’s CAPTCHA
Pick random letters
Distort them, add noise and background
Simard’s HIP
Pick random letters and numbers
Distort them and add arcs
Text Based CAPTCHAs
ISSUES OF TEXT-BASED CAPTCHAS
Audio CAPTCHA
In audio CAPTCHAs, this often means text is synthesized and mixed in with background noise, such as music.
These were initially created to enable people that are visually impaired to register or make use of service that requires solving of a Captcha
Used in restricting Spam over internet Telephony
Spam over IP Telephony: SPIT
Fear of SPIT
With VoIP, costs per call initiation will reduce dramatically
Very low costs are the main reason why e-mail spam is proliferating in the Internet age
 Reasonable to assume that SPIT will become a problem when VoIP gets massively deployed
SPIT is much more obtrusive than e-mail spam
E-mails get “pulled” from a server by the user; VoIP calls are “pushed” to the user
your telephone might ring in the middle of the night…
Most successful approaches against spam from the e-mail world will probably not work
Content filtering needs to be done in real-time
Elements of Audio CAPTCHA’s
There are 3 elements in Audio Captchas
1)Vocabulary
2)Background Noise
3)Audio Production
THE PROBLEM WITH CURRENT AUDIO CAPTCHAS
In some cases the human passing rate is only 70%!
To make the CAPTCHAs secure, noise was injected into the audio files making it harder for both computers and humans to pass.
A CAPTCHA is considered broken once a program can pass it 5% of the time.
Since the current audio CAPTCHAs use a limited vocabulary, it was possible for us to collect enough data to train a system that could pass the current audio CAPTCHAs more than 45% of the time.
HOW DID WE TEST THE CURRENT AUDIO CAPTCHAs?
Selected three different types of audio CAPTCHAs: google, reCAPTCHA, and digg
Collected 1000 CAPTCHAs per type of audio CAPTCHA to use for training and testing
Created an ASR system using machine learning techniques
THE ALGORITHM
Input: Audio CAPTCHA as an audio file
Segmentation
Find the highest energy peak, and extract a fixed size segment centered at that peak
Recognition
Extract features from segment
Give segment to classifier and obtain label
Stop extracting segments once all segments have been labeled or a max solution size is reached.
ANALYSIS OF CURRENT AUDIO CAPTCHAs
Using three machine learning techniques to perform ASR on the CAPTCHAs
AdaBoost
Support Vector Machines (SVM)
k-Nearest Neighbor (k-NN)
THE GOAL
Make a secure audio CAPTCHA which will be easier for a human to pass and harder for a computer to pass.
Equate solving a CAPTCHA with doing some useful work.
In other words, create an audio reCAPTCHA.
WHAT IS reCAPTCHA?
reCAPTCHA helps digitize text on which OCR fails by using the text as its CAPTCHA.
Since millions of people solve CAPTCHAs each day, millions of words get digitized each day!
THE AUDIO RECAPTCHA
Takes advantage of the human ability to understand words through context.
Will help transcribe digital audio on which ASR systems fail.
The audio being used was originally recorded with the intention that it should be easily understood by humans.