Research Article

A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs

See allHide authors and affiliations

Science  08 Dec 2017:
Vol. 358, Issue 6368, eaag2612
DOI: 10.1126/science.aag2612

You are currently viewing the editor's summary.

View Full Text

Log in to view the full text

Log in through your institution

Log in through your institution

Computer or human?

Proving that we are human is now part of many tasks that we do on the internet, such as creating an email account, voting in an online poll, or even downloading a scientific paper. One of the most popular tests is text-based CAPTCHA, where would-be users are asked to decipher letters that may be distorted, partially obscured, or shown against a busy background. This test is used because computers find it tricky, but (most) humans do not. George et al. developed a hierarchical model for computer vision that was able to solve CAPTCHAs with a high accuracy rate using comparatively little training data. The results suggest that moving away from text-based CAPTCHAs, as some online services have done, may be a good idea.

Science, this issue p. eaag2612