Breaking CAPTCHAs with Convolutional Neural Networks

This paper studies reverse Turing tests to distinguish humans and computers, called CAPTCHA. Contrary to classical Turing tests, in this case the judge is not a human but a computer. The main purpose of such tests is securing user logins against the dictionary or brute force password guessing, avoiding automated usage of various services, preventing bots from spamming on forums and many others. Typical approaches to solving text-based CAPTCHA automatically are based on a scheme specific pipeline containing hand-designed pre-processing, denoising, segmentation, post processing and optical character recognition. Only the last part, optical character recognition, is usually based on some machine learning algorithm. We present an approach using neural networks and a simple clustering algorithm that consists of only two steps, character localisation and recognition. We tested our approach on 11 different schemes selected to present very diverse security features. We experimentally show that using convolutional neural networks is superior to multi-layered perceptrons.

[1]  Koray Kavukcuoglu,et al.  Visual Attention , 2020, Computational Models for Cognitive Vision.

[2]  Daniel Cremers,et al.  CAPTCHA Recognition with Active Deep Learning , 2015 .

[3]  Oleg Starostenko,et al.  Breaking reCAPTCHAs with Unpredictable Collapse: Heuristic Character Segmentation and Recognition , 2012, MCPR.

[4]  Mary Czerwinski,et al.  Designing human friendly human interaction proofs (HIPs) , 2005, CHI.

[5]  J. Shaffer.  Multiple Hypothesis Testing , 1995 .

[6]  John C. Mitchell,et al.  Text-based CAPTCHA strengths and weaknesses , 2011, CCS '11.

[7]  John C. Mitchell,et al.  How Good Are Humans at Solving CAPTCHAs? A Large Scale Evaluation , 2010, 2010 IEEE Symposium on Security and Privacy.

[8]  S. Holm.  A Simple Sequentially Rejective Multiple Test Procedure , 1979 .

[9]  John Langford,et al.  CAPTCHA: Using Hard AI Problems for Security , 2003, EUROCRYPT.

[10]  Christoph H. Lampert,et al.  Beyond sliding windows: Object localization by efficient subwindow search , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  John C. Mitchell,et al.  The End is Nigh: Generic Solving of Text-based CAPTCHAs , 2014, WOOT.

[12]  M. Friedman.  The Use of Ranks to Avoid the Assumption of Normality Implicit in the Analysis of Variance , 1937 .

[13]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[14]  Yaroslav Bulatov,et al.  Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks , 2013, ICLR.

[15]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.