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.