Breaking CAPTCHAs with Convolutional Neural Networks

0478627 - ÚI 2018 RIV DE eng C - Konferenční příspěvek (zahraniční konf.)
Kopp, M. - Nikl, M. - Holeňa, Martin
Breaking CAPTCHAs with Convolutional Neural Networks.
Proceedings ITAT 2017: Information Technologies - Applications and Theory. Aachen & Charleston: Technical University & CreateSpace Independent Publishing Platform, 2017 - (Hlaváčová, J.), s. 93-99. CEUR Workshop Proceedings, V-1885. ISBN 978-1974274741. ISSN 1613-0073.
[ITAT 2017. Conference on Theory and Practice of Information Technologies - Applications and Theory /17./. Martinské hole (SK), 22.09.2017-26.09.2017]
Grant CEP: GA ČR GA17-01251S
Grant ostatní: ČVUT(CZ) SGS17/210/OHK3/3T/18
Institucionální podpora: RVO:67985807
Klíčová slova: CAPTCHA * convolutional neural network * network security * optical character recognition
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
http://ceur-ws.org/Vol-1885/93.pdf

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.
Trvalý link: http://hdl.handle.net/11104/0274764