A low-cost attack on a Microsoft captcha
By Jeff Yan, Ahmad Salah El Ahmad. Conference on Computer and Communications Security, 2008
473 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Information Systems, Signal Processing
View Paper: https://www.semanticscholar.org/paper/ce272168776182286103a24ad411276773672f40
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Elie Bursztein
- Angelos Dennis Keromytis
- Matthieu Martin
- Jonathan Aigrain
- John C. Mitchell
- Iasonas Polakis
- Suphannee Sivakorn
- Philippe Golle
In Information Systems
- Elie Bursztein
- John C. Mitchell
- Matthieu Martin
- Angelos Dennis Keromytis
- Jonathan Aigrain
- Iasonas Polakis
- Suphannee Sivakorn
- Philippe Golle
In Signal Processing
- Elie Bursztein
- John C. Mitchell
- Matthieu Martin
- Angelos Dennis Keromytis
- Jonathan Aigrain
- Philippe Golle
- A. Moscicki
Citations in the corpus
- The End is Nigh: Generic Solving of Text-based CAPTCHAs (2014, methodology): “The other method of choice to prevent segmentation, which seems to have fallen out of fashion after a successful wave of attacks [47], is to use occluding lines.”
- Machine learning attacks against the Asirra CAPTCHA (2008, background): “Very recent work [17] gives a detailed description of character segmentation attacks against Microsoft and Yahoo! CAPTCHAs.”
- I am Robot: (Deep) Learning to Break Semantic Image CAPTCHAs (2016, background): “Yan and Ahmad [27] presented an attack against a Microsoft captcha.”
- Text-based CAPTCHA strengths and weaknesses (2011, methodology): “Reflecting on techniques described in the literature [10, 32], available machine-learning techniques [11, 20, 26] available vision algorithms [1, 13, 14], and our own experience with captcha analysis [2, 4, 5], we divide the automated captcha-solving process into five generic steps: pre-processing, ”