Conference Paper

Asirra: A CAPTCHA that exploits interest-aligned manual image categorization

DOI: 10.1145/1315245.1315291 Conference: Proceedings of the 2007 ACM Conference on Computer and Communications Security, CCS 2007, Alexandria, Virginia, USA, October 28-31, 2007
Source: DBLP

ABSTRACT

We present Asirra (Figure 1), a CAPTCHA that asks users to identify cats out of a set of 12 photographs of both cats and dogs. Asirra is easy for users; user studies indicate it can be solved by humans 99.6% of the time in under 30 seconds. Barring a major advance in machine vision, we expect computers will have no better than a 1/54,000 chance of solving it. Asirra’s image database is provided by a novel, mutually beneficial partnership with Petfinder.com. In exchange for the use of their three million images, we display an “adopt me” link beneath each one, promoting Petfinder’s primary mission of finding homes for homeless animals. We describe the design of Asirra, discuss threats to its security, and report early deployment experiences. We also describe two novel algorithms for amplifying the skill gap between humans and computers that can be used on many existing CAPTCHAs.

  • Source
    • "CAPTCHA tests are based on open and hard problems in AI [4] , which include recognition of highly distorted images, answering problems that require semantic knowledge [10], without giving a learning set to the bot. CAPTCHA itself has been developed into many variants by various individuals and organizations like Google [11] and Microsoft [12]. reCAPTCHA [11] aims to convert images of old books and manuscripts to text alongside a normal CAPTCHA image etc. "

    Full-text · Dataset · Feb 2016
  • Source
    • "[cs.CV] 13 Sep 2015 The challenge is to distinguish between cats and dogs on the Asirra CAPTCHA [10], a dataset for an already-finished competition hosted by Kaggle. The task is easy for humans, while designed to be presumably difficult to be accomplished automatically [10]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Convolutional neural networks are becoming standard tools for solving object recognition and visual tasks. However, most of the design and implementation of these complex models are based on trail-and-error. In this report, the main focus is to consider some of the important factors in designing convolutional networks to perform better. Specifically, classification with wide single-layer networks with large kernels as a general framework is considered. Particularly, we will show that pre-training using unsupervised schemes is vital, reasonable regularization is beneficial and applying of strong regularizers like dropout could be devastating. Pool size is also could be as important as learning procedure itself. In addition, it has been presented that using such a simple and relatively fast model for classifying cats and dogs, performance is close to state-of-the-art achievable by a combination of SVM models on color and texture features.
    Preview · Article · Sep 2015
  • Source
    • "Image recognition Captchas is usually database-based method, thus requiring a database of predetermined images. Microsoft's Asirra is a wellknown example [10]. Asirra presents a list of (or) collection of animal images such as cat and dog etc., images, asking the user to identify the those images and which are entered in the form of characters. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Abstract- User authentication has become one of the important topics in information security. Many graphical password schemes have been proposed, which are used to improve password usability and security. In this paper, we present a new approach to solve the hard AI problems, namely, graphical passwords are combined with Captcha technique, which will be referred them as Captcha as graphical password otherwise we call it as CaRP. CaRP solves security problems such as online dictionary attacks, relay attacks and shoulder-surfing attacks combined with dual-view technologies. Captcha as graphical passwords also offers an efficient approach to address the well-known image hotspot problem in popular graphical password systems, such as Pass-Points. CaRP also offers primitive scheme to provide reasonable and usability security to improve online security.
    Full-text · Article · Aug 2015
Show more