Date of Award

12-2011

Degree Type

Report

Degree Name

Master of Science (MS)

Department

Computer Science

Committee Chair(s)

Donald Cooley

Committee

Donald Cooley

Committee

Stephen Clyde

Committee

Nicholas Flann

Abstract

A CAPTCHA is a specialized human interaction proof that exploits gaps between human and computer recognition abilities. By design, the hardness of a CAPTCHA is based on the difficulty of advancing the underlying artificial intelligence [AI] technology to a level that eliminates any exploitable gap. Due to this fact computer scientists have concluded that the widespread use of CAPTCHA would accelerate research in the underlying fields of AI eventually leading to near-­‐human capabilities in certain AI systems. Despite these predictions no attempt has been made to identify advances in AI which can be attributed to the use of CAPTCHA.

The goal of this report is to explore the concept of CAPTCHA as a catalyst for advancement in AI. As part of this goal I examine the underlying basis for expected contributions, provide direct examples of documented advancements that have already been made, evaluate the strengths and weaknesses of the CAPTCHA model and based on the results identify specific areas of AI most likely to benefit from CAPTCHA in the future.

As a result of my research I have found that some advancement has been made as a result of CAPTCHA, but due to weaknesses in many CAPTCHA implementations these advancements have been limited and have often fallen short of expectations. As many of these weaknesses have been identified new methods of implementation have been introduced, but many of these have limitations as well. As part of the exploration of these challenges I have provided a basis that will allow for a more accurate understanding of the processes involved, and allow others to continue to build on the work which has already been done.

Comments

This work made publicly available electronically on November 21, 2011.

Download

Share

COinS

Copyright for this work is retained by the student. If you have any questions regarding the inclusion of this work in the Digital Commons, please email us at .