The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
How Good Are Humans at Solving CAPTCHAs? A Large Scale Evaluation
Abstract
Captchas are designed to be easy for humans but hard for machines. However, most recent research has focused only on making them hard for machines. In this paper, we present what is to the best of our knowledge the first large scale evaluation of captchas from the human perspective, with the goal of assessing how much friction captchas present to the average user. For the purpose of this study we have asked workers from Amazon's Mechanical Turk and an underground captchabreaking service to solve more than 318 000 captchas issued from the 21 most popular captcha schemes (13 images schemes and 8 audio scheme). Analysis of the resulting data reveals that captchas are often difficult for humans, with audio captchas being particularly problematic. We also find some demographic trends indicating, for example, that non-native speakers of English are slower in general and less accurate on English-centric captcha schemes. Evidence from a week's worth of eBay captchas (14,000,000 samples) suggests that the solving accuracies found in our study are close to real-world values, and that improving audio captchas should become a priority, as nearly 1% of all captchas are delivered as audio rather than images. Finally our study also reveals that it is more effective for an attacker to use Mechanical Turk to solve captchas than an underground service.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
CAPTCHA: Using Hard AI Problems for Security
von Ahn, L., Blum, M., Hopper, N. J., & Langford, J. (2003) · Lecture Notes in Computer Science · doi:10.1007/3-540-39200-9_18 · Cited by 1,447
Recognizing objects in adversarial clutter: breaking a visual CAPTCHA
Mori, G., & Malik, J. (2003) · 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings. · doi:10.1109/cvpr.2003.1211347 · Cited by 596
Asirra: A captcha that exploits interest-aligned manual image categorization
Elson, J., Douceur, J. R., Howell, J., & Saul, J. (2007) · Cited by 479
A low-cost attack on a Microsoft captcha
Yan, J., & El Ahmad, A. S. (2008) · Proceedings of the 15th ACM conference on Computer and communications security · doi:10.1145/1455770.1455839 · Cited by 399
Machine learning attacks against the Asirra CAPTCHA
Golle, P. (2008) · Proceedings of the 15th ACM conference on Computer and communications security · doi:10.1145/1455770.1455838 · Cited by 234
Evaluating existing audio CAPTCHAs and an interface optimized for non-visual use
Bigham, J. P., & Cavender, A. C. (2009) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1518701.1518983 · Cited by 187
Building Segmentation Based Human-Friendly Human Interaction Proofs (HIPs)
Chellapilla, K., Larson, K., Simard, P. Y., & Czerwinski, M. P. (2005) · Lecture notes in computer science · doi:10.1007/11427896_1 · Cited by 155
Datta, R., Li, J., & Wang, J. Z. (2005) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/1101149.1101218 · Cited by 136
ScatterType: a reading CAPTCHA resistant to segmentation attack
Baird, H. S., & Riopka, T. P. (2005) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.587811 · Cited by 65
Cited by
Data Collection in the Digital Age: Innovative Alternatives to Student Samples1
Steelman, Z. R., Hammer, B. I., & Limayem, M. (2014) · MIS Quarterly · doi:10.25300/misq/2014/38.2.02 · Cited by 405
Ahmad, I., Shahabuddin, S., Kumar, T., Okwuibe, J., Gurtov, A., & Ylianttila, M. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2916180 · Cited by 366
Text-based CAPTCHA strengths and weaknesses
Bursztein, E., Martin, M., & Mitchell, J. (2011) · Proceedings of the 18th ACM conference on Computer and communications security · doi:10.1145/2046707.2046724 · Cited by 340
Self-citationRobotic foot-in-the-door: Using sequential-request persuasive strategies in human-robot interaction
Lee, S. A., & Liang, Y. (. (2019) · Computers in Human Behavior · doi:10.1016/j.chb.2018.08.026 · Cited by 52
Practicality analysis of utilizing text-based CAPTCHA vs. graphic-based CAPTCHA authentication
Gutub, A., & Kheshaifaty, N. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15586-5 · Cited by 21
Metadata
- Authors
- Bursztein, E., Bethard, S., Fabry, C., Mitchell, J. C., & Jurafsky, D.
- Venue
- 2010 IEEE Symposium on Security and Privacy
- Publisher
- IEEE
- Published
- 2010
- Pages
- 399-413
- ISSN
- 1081-6011 (ISSN-L)
- OpenAlex
- W2084062832
- Cited by
- 254
- References
- 9
- FWCI
- 16.42
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: How Good Are Humans at Solving CAPTCHAs? A Large Scale Evaluation. https://app.cochat.ai/papers/10.1109/sp.2010.31
- The paper
- Bursztein, E., Bethard, S., Fabry, C., Mitchell, J. C., & Jurafsky, D. (2010). How Good Are Humans at Solving CAPTCHAs? A Large Scale Evaluation. 2010 IEEE Symposium on Security and Privacy. https://doi.org/10.1109/sp.2010.31
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.