TY - GEN
T1 - Text-based CAPTCHA Vulnerability Assessment using a Deep Learning-based Solver
AU - Aguilar, Daniel
AU - Riofrío, Daniel
AU - Benítez, Diego
AU - Pérez, Noel
AU - Moyano, Ricardo Flores
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/10/12
Y1 - 2021/10/12
N2 - The focus of this work is to test the security offered by Text-based CAPTCHAs. We present different types of CAPTCHAs and a preprocessing and segmentation process to clean noise in CAPTCHA images and crop digits or characters in single images. We present a convolutional neural network architecture trained under several hyperparameters, comparing multiple models with different batch sizes, epochs, and optimizers. We confirmed that using Text-based CAPTCHAs is no longer a secure mechanism for protection because, with simple computer vision techniques and current machine learning algorithms, they can be broken. We achieved a 90.49% accuracy with our model trained with a mix of four datasets and up to 97.10% with one dataset, which is enough to consider these schemes insecure in practice.
AB - The focus of this work is to test the security offered by Text-based CAPTCHAs. We present different types of CAPTCHAs and a preprocessing and segmentation process to clean noise in CAPTCHA images and crop digits or characters in single images. We present a convolutional neural network architecture trained under several hyperparameters, comparing multiple models with different batch sizes, epochs, and optimizers. We confirmed that using Text-based CAPTCHAs is no longer a secure mechanism for protection because, with simple computer vision techniques and current machine learning algorithms, they can be broken. We achieved a 90.49% accuracy with our model trained with a mix of four datasets and up to 97.10% with one dataset, which is enough to consider these schemes insecure in practice.
KW - Computer Vision
KW - Convolutional Neural Networks
KW - Deep Learning
KW - LeNet
KW - Text-Based CAPTCHAs
UR - https://www.scopus.com/pages/publications/85119429074
U2 - 10.1109/ETCM53643.2021.9590750
DO - 10.1109/ETCM53643.2021.9590750
M3 - Contribución a la conferencia
AN - SCOPUS:85119429074
T3 - ETCM 2021 - 5th Ecuador Technical Chapters Meeting
BT - ETCM 2021 - 5th Ecuador Technical Chapters Meeting
A2 - Huerta, Monica Karel
A2 - Quevedo, Sebastian
A2 - Monsalve, Carlos
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th IEEE Ecuador Technical Chapters Meeting, ETCM 2021
Y2 - 12 October 2021 through 15 October 2021
ER -