Telling humans and computers apart automatically

By Luis von Ahn, Manuel Blum, J. Langford. CACM, 2004

977 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Signal Processing

View Paper: https://www.semanticscholar.org/paper/462a5d45ff33a40078f92fb358344419af87f351

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jitendra Malik
2. Greg Mori
3. Li Fei-Fei
4. Serge J. Belongie
5. Roberto Cipolla
6. José Hernandez-Orallo
7. Luc Van Gool
8. Trevor Darrell

In Information Systems

1. José Hernandez-Orallo
2. Greg Mori
3. Jitendra Malik
4. Serge J. Belongie
5. Arthur W. Berger
6. Jaeyeon Jung
7. Stuart E. Schechter
8. Jeff Yan

In Signal Processing

1. José Hernandez-Orallo
2. Jitendra Malik
3. Greg Mori
4. Stuart E. Schechter
5. Jaeyeon Jung
6. Arthur W. Berger
7. Matteo Dell'Amico
8. Pietro Michiardi

Citations in the corpus

• Fast Detection of Scanning Worm Infections (2004, methodology): “We propose that HTTP requests from such hosts be redirected to a site that uses a CAPTCHA (Completely Automated Public Turing Test to Tell Computers and Humans Apart [23]), to confirm that a user is present and was using a Web browser at the time of quarantine.”
• Usability of CAPTCHAs or usability issues in CAPTCHA design (2008, background): “However, distortion is absent in some image­based schemes (e.g. Assira [25] and Bongo [1]) - for these schemes, only the dimensions of content and presentation matter.”
• Efficient shape matching using shape contexts (2005, background): “8) is a CAPTCHA based on word recognition in the presence of clutter.”
• Evaluation in artificial intelligence: from task-oriented to ability-oriented measurement (2017, methodology): “Other highly subjective properties may also be of interest: enjoyability, resilience, aggressiveness, fun, etc. Finally, there is a kind of test that is related to the Turing Test, the so-called CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) (von Ahn et al, 2004”
• Recognizing objects in adversarial clutter: breaking a visual CAPTCHA (2003, methodology): “A CAPTCHA is a program [ 19 ] that can generate and grade tests that:”
• CAPTCHA: Using Hard AI Problems for Security (2003, background): “A related general interest paper [ 2 ] has been accepted by Communications of the ACM.”
• Password Strength: An Empirical Analysis (2010, background): “• CAPTCHAs [13], which require solving puzzles that are difficult without human intervention; • key strengthening techniques, which require a few seconds of computation to derive a key from the passwords.”
• Shape context and chamfer matching in cluttered scenes (2003, background): “Automatic recognition is made difficult specifically for the task to tell humans and computers apart [18].”
• Prototype-Incorporated Emotional Neural Network (2018, background): “Inasmuch as these tasks are somewhat “trivial” for humans, machines strive to perform competitively [7], [8].”