Multiview deep learning-based attack to break text-CAPTCHAs

Abstract

Completely Automated Public Turing Test To Tell Computer and Humans Apart (CAPTCHA) is a computer program that prevents malicious computer users. Text-CAPTCHA schemes utilize less-computational costs. Hence, they are the most popularly used. This paper investigates the effectiveness of state-of-the-art (SOTA) text-CAPTCHA schemes, proposes a Multiview deep learning system to break them, and highlights their weaknesses. Rather than the usual single-view feature extraction, the proposed model explores correlational features from multiple views to increase the model’s generalization and classification accuracy. The model combines convolutional neural networks and recurrent networks to preserve the input text-CAPTCHA’s spatial and sequential order. The proposed system has successfully achieved average accuracies ranging from 93.6% to 100%, and the average time to break a text-CAPTCHA scheme ranges from 0.0032 to 0.21 seconds on eight different datasets. Furthermore, an ablation study on 71 human users was conducted to evaluate the effectiveness of the schemes. The results demonstrated that the proposed system effectively outperforms the human users whom the schemes were designed to serve. Lastly, when compared with existing systems, the proposed system outperforms existing SOTA systems with an accuracy gap of almost 40% higher.

A videoconferencing verification method for enrollment of breastfeeding dyads to an online prospective mixed methods study during the COVID‐19 pandemic

“…Computer programs, such as internet “bots”, have been able to bend CAPTCHAs since before 2017 (George et al., 2017). With the recent rapid advancement and current availability of artificial intelligence programs, CAPTCHAs are no longer as much of a barrier to preventing automated responses (Yusuf et al., 2023). Originally, the project's REDCap was not protected with a CAPTCHA, and once added the first round of fraudulent responses was terminated.…”

Adaptive CAPTCHA: A CRNN-Based Text CAPTCHA Solver with Adaptive Fusion Filter Networks

“…Mukhtar Opeyemi Yusuf et al introduced a multiview deep learning method for cracking CAPTCHAs. This approach utilizes correlational characteristics from many perspectives to enhance the model's ability to generalize and accurately classify [25]. A method was proposed by Zaid Derea et al for recognizing CAPTCHAs that involves making several copies of the original CAPTCHA pictures and producing individual binary images with the precise positions of each set of CAPTCHA letters [26].…”