Team for Research in
Ubiquitous Secure Technology

Citation
Elie Bursztein, Romain Beauxis, Hristo Peskov, Daniele Perito, Celine Fabry. "The Failure of Noise-Based Non-continuous Audio Captchas". IEEE Symposium on Security and Policy, pp.19-31, 22, May, 2011.

Abstract
CAPTCHAs, which are automated tests intended to distinguish humans from programs, are used on many web sites to prevent bot-based account creation and spam. To avoid imposing undue user friction, CAPTCHAs must be easy for humans and difficult for machines. However, the scientific basis for successful CAPTCHA design is still emerging. This paper examines the widely used class of audio CAPTCHAs based on distorting non-continuous speech with certain classes of noise and demonstrates that virtually all current schemes, including ones from Microsoft, Yahoo, and eBay, are easily broken. More generally, we describe a set of fundamental techniques, packaged together in our Decaptcha system, that effectively defeat a wide class of audio CAPTCHAs based on non-continuous speech. Decaptcha's performance on actual observed and synthetic CAPTCHAs indicates that such speech CAPTCHAs are inherently weak and, because of the importance of audio for various classes of users, alternative audio CAPTCHAs must be developed.

Electronic downloads

• http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=5958019&url=http%3A%2F%2Fieeexplore.ieee.org%2Fxpls%2Fabs_all.jsp%3Farnumber%3D5958019

• HTML

  Elie Bursztein, Romain Beauxis, Hristo Peskov, Daniele
  Perito, Celine Fabry. <a
  href="http://www.truststc.org/pubs/893.html"
  >The Failure of Noise-Based Non-continuous Audio
  Captchas</a>, IEEE Symposium on Security and Policy,
  pp.19-31, 22, May, 2011.

• Plain text

  Elie Bursztein, Romain Beauxis, Hristo Peskov, Daniele
  Perito, Celine Fabry. "The Failure of Noise-Based
  Non-continuous Audio Captchas". IEEE Symposium on
  Security and Policy, pp.19-31, 22, May, 2011.

• BibTeX

  @inproceedings{BurszteinBeauxisPeskovPeritoFabry11_FailureOfNoiseBasedNoncontinuousAudioCaptchas,
      author = {Elie Bursztein and Romain Beauxis and Hristo
                Peskov and Daniele Perito and Celine Fabry},
      title = {The Failure of Noise-Based Non-continuous Audio
                Captchas},
      booktitle = {IEEE Symposium on Security and Policy},
      pages = {pp.19-31},
      day = {22},
      month = {May},
      year = {2011},
      abstract = {CAPTCHAs, which are automated tests intended to
                distinguish humans from programs, are used on many
                web sites to prevent bot-based account creation
                and spam. To avoid imposing undue user friction,
                CAPTCHAs must be easy for humans and difficult for
                machines. However, the scientific basis for
                successful CAPTCHA design is still emerging. This
                paper examines the widely used class of audio
                CAPTCHAs based on distorting non-continuous speech
                with certain classes of noise and demonstrates
                that virtually all current schemes, including ones
                from Microsoft, Yahoo, and eBay, are easily
                broken. More generally, we describe a set of
                fundamental techniques, packaged together in our
                Decaptcha system, that effectively defeat a wide
                class of audio CAPTCHAs based on non-continuous
                speech. Decaptcha's performance on actual observed
                and synthetic CAPTCHAs indicates that such speech
                CAPTCHAs are inherently weak and, because of the
                importance of audio for various classes of users,
                alternative audio CAPTCHAs must be developed. },
      URL = {http://www.truststc.org/pubs/893.html}
  }
  

Posted by Mary Stewart on 4 Apr 2012.
For additional information, see the Publications FAQ or contact webmaster at www truststc org.