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.

1 Bookmark
 · 
101 Views
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: For the last ten years, CAPTCHAs have been widely used by websites to prevent their data being automatically updated by machines. By supposedly allowing only humans to do so, CAPTCHAs take advantage of the reverse Turing test (TT), knowing that humans are more intelligent than machines. Generally, CAPTCHAs have defeated machines, but things are changing rapidly as technology improves. Hence, advanced research into optical character recognition (OCR) is overtaking attempts to strengthen CAPTCHAs against machine-based attacks. This paper investigates the immunity of CAPTCHA, which was built on the failure of the TT. We show that some CAPTCHAs are easily broken using a simple OCR machine built for the purpose of this study. By reviewing other techniques, we show that even more difficult CAPTCHAs can be broken using advanced OCR machines. Current advances in OCR should enable machines to pass the TT in the image recognition domain, which is exactly where machines are seeking to overcome CAPTCHAs. We enhance traditional CAPTCHAs by employing not only characters, but also natural language and multiple objects within the same CAPTCHA. The proposed CAPTCHAs might be able to hold out against machines, at least until the advent of a machine that passes the TT completely.
    European Scientific Journal. 09/2014; 10(15).
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: CAPTCHAs(Completely Automated Public Turing tests to tell Computer and Human Apart) have been widely used for preventing the automated attacks such as spam mails, DDoS attacks, etc.. In the early stages, the text-based CAPTCHAs that were made by distorting random characters were mainly used for frustrating automated-bots. Many researches, however, showed that the text-based CAPTCHAs were breakable via AI or image processing techniques. Due to the reason, the image-based CAPTCHAs, which employ images instead of texts, have been considered and suggested. In many image-based CAPTCHAs, however, the huge number of source images are required to guarantee a fair level of security. In 2008, Kang et al. suggested a new image-based CAPTCHA that uses test images made by composing multiple source images, to reduce the number of source images while it guarantees the security level. In their paper, the authors showed the convenience of their CAPTCHA in use through the use study, but they did not verify its security level. In this paper, we verify the security of the image-based CAPTCHA suggested by Kang et al. by performing several attacks in various scenarios and consider other possible attacks that can happen in the real world.
    Journal of the Korea Institute of Information Security and Cryptology. 01/2012; 22(4).
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Telephony systems are imperative for information exchange offering low cost services and reachability to millions of customers. They have not only benefited legitimate users but have also opened up a convenient communication medium for spammers. Voice spam is often encountered on telephony systems in various forms, such as by means of an automated telemarketing call asking to call a number to win a reward. A large percentage of voice spam is generated through automated system which introduces the classical challenge of distinguishing machines from humans on telephony systems. CAPTCHA is a conventional solution deployed on the web to address this problem. Audio-based CAPTCHAs have been proposed as a solution to curb voice spam. In this paper, we conducted a field study with 90 participants in order to answer two primary research questions: quantifying the amount of inconvenience telephony-based CAPTCHA may cause to users, and how various features of the CAPTCHA, such as duration and size, influence usability of telephony-based CAPTCHA. Our results suggest that currently proposed CAPTCHAs are far from usable, with very low solving accuracies, high solving times and poor overall user experience. We provide certain guidelines that may help improve existing CAPTCHAs for use in telephony systems.
    The 16th Information Security Conference, Dallas, Texas; 11/2013

Full-text

Download
5 Downloads
Available from