ABSTRACT
HIPs, or Human Interactive Proofs, are challenges meant to be easily solved by humans, while remaining too hard to be economically solved by computers. HIPs are increasingly used to protect services against automatic script attacks. To be effective, a HIP must be difficult enough to discourage script attacks by raising the computation and/or development cost of breaking the HIP to an unprofitable level. At the same time, the HIP must be easy enough to solve in order to not discourage humans from using the service. Early HIP designs have successfully met these criteria [1]. However, the growing sophistication of attackers and correspondingly increasing profit incentives have rendered most of the currently deployed HIPs vulnerable to attack [2,7,12]. Yet, most companies have been reluctant to increase the difficulty of their HIPs for fear of making them too complex or unappealing to humans. The purpose of this study is to find the visual distortions that are most effective at foiling computer attacks without hindering humans. The contribution of this research is that we discovered that 1) automatically generating HIPs by varying particular distortion parameters renders HIPs that are too easy for computer hackers to break, yet humans still have difficulty recognizing them, and 2) it is possible to build segmentation-based HIPs that are extremely difficult and expensive for computers to solve, while remaining relatively easy for humans.
- Simard PY, Szeliski R, Benaloh J, Couvreur J, and Calinov I (2003), "Using Character Recognition and Segmentation to Tell Computers from Humans," Intl. Conf. on Document Analysis and Recognition (ICDAR), IEEE Computer Society, pp. 418--423, 2003. Google ScholarDigital Library
- Chellapilla K., and Simard P., "Using Machine Learning to Break Visual Human Interaction Proofs (HIPs)," Advances in Neural Information Processing Systems 17, Neural Information Processing Systems (NIPS'2004), MIT Press.Google Scholar
- Turing AM (1950), "Computing Machinery and Intelligence," Mind, vol. 59, no. 236, pp. 433--460.Google ScholarCross Ref
- Von Ahn L, Blum M, and Langford J. (2004) "Telling Computers and Humans Apart (Automatically) or How Lazy Cryptographers do AI." Comm. of the ACM, 47(2):56--60. Google ScholarDigital Library
- First Workshop on Human Interactive Proofs, Palo Alto, CA, January 2002.Google Scholar
- Von Ahn L, Blum M, and Langford J, The Captcha Project. http://www.captcha.netGoogle Scholar
- Mori G, Malik J (2003), "Recognizing Objects in Adversarial Clutter: Breaking a Visual CAPTCHA," Proc. of Comp. Vision and Pattern Rec. (CVPR) Conf., IEEE Computer Society, vol.1, pages:I-134 - I-141, June 18-20, 2003. Google ScholarDigital Library
- Chew, M. and Baird, H. S. (2003), "BaffleText: a Human Interactive Proof," Proc. 10th IS&T/SPIE Doc. Reco. & Retrieval Conf., Santa Clara, CA, Jan. 22.Google Scholar
- Simard, P.,Y., Steinkraus, D., Platt, J. (2003) "Best Practice for Convolutional Neural Networks Applied to Visual Document Analysis," International Conference on Document Analysis and Recognition (ICDAR), IEEE Computer Society, Los Alamitos, pp. 958--962, 2003. Google ScholarDigital Library
- Selfridge, O.G. (1959). Pandemonium: A paradigm for learning. In Symposium in the mechanization of thought process (pp.513-526). London: HM Stationery Office.Google Scholar
- Pelli, D. G., Burns, C. W., Farrell, B., & Moore, D. C, "Identifying letters." (accepted) Vision Research.Google Scholar
- Goodman J. and Rounthwaite R., "Stopping Outgoing Spam," Proc. of the 5th ACM conf. on Electronic commerce, New York, NY. 2004. Google ScholarDigital Library
Index Terms
- Designing human friendly human interaction proofs (HIPs)
Recommendations
Building segmentation based human-friendly human interaction proofs (HIPs)
HIP'05: Proceedings of the Second international conference on Human Interactive ProofsHuman 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 ...
Leveraging human computation for pure-text Human Interaction Proofs
Even though purely text-based Human Interaction Proofs (HIPs) have desirable usability and accessibility attributes; they could not overcome the security problems yet. Given the fact that fully automated techniques to generate pure-text HIPs securely do ...
Pictorial Human Spaces: A Computational Study on the Human Perception of 3D Articulated Poses
Human motion analysis in images and video, with its deeply inter-related 2D and 3D inference components, is a central computer vision problem. Yet, there are no studies that reveal how humans perceive other people in images and how accurate they are. In ...
Comments