Abstract
Human interaction proofs (HIPs) have become common place on the internet due to their effectiveness in deterring automated abuse of online services intended for humans. However, there is a co-evolutionary arms race in progress and these proofs are becoming more difficult for genuine users while attackers are getting better at breaking existing HIPs. We studied various popular HIPs on the internet to understand their strength and human friendliness. To determine HIP strength, we adopted a direct approach of building computer attacks using image processing and machine learning techniques. To understand human-friendliness, a sequence of users studies were conducted to investigate HIP character recognition by humans under a variety of visual distortions and clutter commonly employed in reading-based HIPs. We found that many of the online HIPs are pure recognition tasks that can be easily broken using machine learning. The stronger HIPs tend to pose a combination of segmentation and recognition challenges. Further, the HIP user studies show that given correct segmentation, computers are much better at HIP character recognition than humans. In light of these results, we propose that segmentation-based reading challenges are the future for building stronger human-friendly HIPs. An example of such a segmentation-based HIP is presented with a preliminary assessment of its strength and human-friendliness.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Baird, H.S.: Anatomy of a versatile page reader. IEEE Proceedings 80, 1059–1065 (1992)
Chellapilla, K., Simard, P.: Using Machine Learning to Break Visual Human Interaction Proofs (HIPs). In: NIPS 2004, MIT Press, Cambridge (2004)
First Workshop on Human Interactive Proofs, Palo Alto, CA (January 2002)
Von Ahn, L., Blum, M., Langford, J.: The Captcha Project, http://www.captcha.net
Baird, H.S., Popat, K.: Human Interactive Proofs and Document Image Analysis. In: Proc. IAPR 2002 Workshop on Document Analysis Systems, Princeton, NJ (2002)
Simard, P.Y., Steinkraus, D., Platt, J.: Best Practice for Convolutional Neural Networks Applied to Visual Document Analysis. In: ICDAR 2003, pp. 958–962. IEEE Computer Society, Los Alamitos (2003)
Mori, G., Malik, J.: Recognizing Objects in Adversarial Clutter: Breaking a Visual CAPTCHA. In: CVPR 2003, vol. 1, pp. I-134–I-141. IEEE Computer Society, Los Alamitos (2003)
Chew, M., Baird, H.S.: BaffleText: a Human Interactive Proof. In: Proc., 10th IS&T/SPIE Document Recognition & Retrieval Conf., Santa Clara, CA, January 22 (2003)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE (November 1998)
Selfridge, O.G.: Pandemonium: A paradigm for learning. In: Symposium in the mechanization of thought process, pp. 513–526. HM Stationery Office, London (1959)
Pelli, D.G., Burns, C.W., Farrell, B., Moore, D.C.: Identifying letters (accepted) Vision Research
Goodman, J., Rounthwaite, R.: Stopping Outgoing Spam. In: Proc. of the 5th ACM conf. on Electronic commerce, New York, NY (2004)
Baird, H.S., Luk, M.: Protecting Websites with Reading-Based CAPTCHAs. In: Second International Web Document Analysis Workshop (WDA 2003), Edinburgh, Scotland, August 3 (2003)
Coates, A.L., Baird, H.S., Fateman, R.J.: Pessimal Print: A Reverse Turing Test. In: Sixth International Conference on Document Analysis and Recognition (ICDAR 2001), Seattle, WA, September 10-13 (2001)
Thayananthan, A., Stenger, B., Torr, P.H.S., Cipolla, R.: Shape Context and Chamfer Matching in Cluttered Scenes. CVPR (1), 127–133 (2003)
Moy, G., Jones, N., Harkless, C., Potter, R.: Distortion Estimation Techniques in Solving Visual CAPTCHAs. In: CVPR 2004, Washington, D.C., USA, June 27-July 02, vol. 2, pp. 23–28 (2004)
Deriche, R.: Fast Algorithms for Low-Level Vision. IEEE Trans. on PAMI 12(1), 78–87 (1990)
Chellapilla, K., Larson, K., Simard, P., Czerwinski, M.: Designing Human Friendly Human Interaction Proofs (HIPs). In: Conference on Human factors In computing systems, CHI 2005, ACM Press, New York (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chellapilla, K., Larson, K., Simard, P.Y., Czerwinski, M. (2005). Building Segmentation Based Human-Friendly Human Interaction Proofs (HIPs). In: Baird, H.S., Lopresti, D.P. (eds) Human Interactive Proofs. HIP 2005. Lecture Notes in Computer Science, vol 3517. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11427896_1
Download citation
DOI: https://doi.org/10.1007/11427896_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26001-1
Online ISBN: 978-3-540-32117-0
eBook Packages: Computer ScienceComputer Science (R0)