Paper 2008/126

Machine Learning Attacks Against the ASIRRA CAPTCHA

Philippe Golle


The ASIRRA CAPTCHA [EDHS2007], recently proposed at ACM CCS 2007, relies on the problem of distinguishing images of cats and dogs (a task that humans are very good at). The security of ASIRRA is based on the presumed difficulty of classifying these images automatically. In this paper, we describe a classifier which is 82.7% accurate in telling apart the images of cats and dogs used in ASIRRA. This classifier is a combination of support-vector machine classifiers trained on color and texture features extracted from images. Our classifier allows us to solve a 12-image ASIRRA challenge automatically with probability 10.3%. This probability of success is significantly higher than the estimate given in [EDHS2007] for machine vision attacks. The weakness we expose in the current implementation of ASIRRA does not mean that ASIRRA cannot be deployed securely. With appropriate safeguards, we believe that ASIRRA offers an appealing balance between usability and security. One contribution of this work is to inform the choice of safeguard parameters in ASIRRA deployments.

Available format(s)
Publication info
Published elsewhere. Unknown where it was published
Contact author(s)
pgolle @ cs stanford edu
2008-03-24: received
Short URL
Creative Commons Attribution


      author = {Philippe Golle},
      title = {Machine Learning Attacks Against the ASIRRA CAPTCHA},
      howpublished = {Cryptology ePrint Archive, Paper 2008/126},
      year = {2008},
      note = {\url{}},
      url = {}
Note: In order to protect the privacy of readers, does not use cookies or embedded third party content.