Breaking CAPTCHA with Capsule Networks

Mocanu, Ionela Georgiana; Yang, Zhenxu; Belle, Vaishak

doi:10.1016/j.neunet.2022.06.041

Cited by 6 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lu et al proposed a skip-connection CNN model using two publicly available datasets of text-based CAPTCHA images, which yields a promising result compared to previous studies [21]. More recently, capsule networks have been used due to their capability of preserving detailed information about the input [22]. Shi et al proposed an RCNN network based on the Connectionist Temporal Classification (CTC) loss function and RNN, which improved the detection ability of variable-length characters [23].…”

Section: Captcha Recognition With Cnn and Rnnmentioning

confidence: 99%

Adaptive-CAPTCHA: A Text CAPTCHA Solver based on CRNN and Configurable Filter Networks

Wan,

Johari,

Ruslan

2024

Preprint

View full text Add to dashboard Cite

Text-based CAPTCHA remains the most widely adopted security scheme, which is the first barrier to securing websites. Deep learning methods, especially Convolutional Neural Networks (CNNs) are the mainstream approach for text-CAPTCHA recognition, which are widely used in CAPTCHA vulnerability assessment and data collection. However, verification code recognizers are mostly deployed on the CPU platform as part of a web crawler and security assessment, they are required to have both low complexity and high recognition accuracy. Due to the specifically designed anti-attack mechanisms like noise, interference, geometric deformation, twisting, rotation, and character adhesion in text CAPTCHAs, some characters are difficult to efficiently identify with high accuracy in these complex CAPTCHA images. This paper proposed a recognition model named Adaptive-CAPTCHA with a CRNN module and trainable and configurable filtering networks, which effectively handle the interference and learn the correlation between characters in CAPTCHAs to enhance recognition accuracy. Experimental results on two datasets of different complexity show that compared with the baseline model Deep-CAPTCHA, the number of parameters of our proposed model is reduced by about 70% and the recognition accuracy is improved by more than 10 percentage points in the two datasets. In addition, the proposed model has a faster training convergence speed.

show abstract

Section: Captcha Recognition With Cnn and Rnnmentioning

confidence: 99%

Adaptive-CAPTCHA: A Text CAPTCHA Solver based on CRNN and Configurable Filter Networks

Wan,

Johari,

Ruslan

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…More recently, capsule networks have been used due to their capability of preserving detailed information about the input [20]. Nevertheless, this approach is extremely computationally intensive, and later trials indicate that the Attack Success Rate (ASR) is not good for CAPTCHAs with significant levels of noise.…”

Section: Captcha Recognition With Cnn and Rnnmentioning

confidence: 99%

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

Wan,

Johari,

Ruslan

2024

Applied Sciences

View full text Add to dashboard Cite

Text-based CAPTCHAs remain the most widely adopted security scheme, which is the first barrier to securing websites. Deep learning methods, especially Convolutional Neural Networks (CNNs), are the mainstream approach for text CAPTCHA recognition and are widely used in CAPTCHA vulnerability assessment and data collection. However, verification code recognizers are mostly deployed on the CPU platform as part of a web crawler and security assessment; they are required to have both low complexity and high recognition accuracy. Due to the specifically designed anti-attack mechanisms like noise, interference, geometric deformation, twisting, rotation, and character adhesion in text CAPTCHAs, some characters are difficult to efficiently identify with high accuracy in these complex CAPTCHA images. This paper proposed a recognition model named Adaptive CAPTCHA with a CNN combined with an RNN (CRNN) module and trainable Adaptive Fusion Filtering Networks (AFFN), which effectively handle the interference and learn the correlation between characters in CAPTCHAs to enhance recognition accuracy. Experimental results on two datasets of different complexities show that, compared with the baseline model Deep CAPTCHA, the number of parameters of our proposed model is reduced by about 70%, and the recognition accuracy is improved by more than 10 percentage points in the two datasets. In addition, the proposed model has a faster training convergence speed. Compared with several of the latest models, the model proposed by the study also has better comprehensive performance.

show abstract

Novel hybrid classifier based on fuzzy type-III decision maker and ensemble deep learning model and improved chaos game optimization

Mehrabi Hashjin,

Amiri,

Mohammadzadeh

et al. 2024

Cluster Comput

View full text Add to dashboard Cite

This paper presents a unique hybrid classifier that combines deep neural networks with a type-III fuzzy system for decision-making. The ensemble incorporates ResNet-18, Efficient Capsule neural network, ResNet-50, the Histogram of Oriented Gradients (HOG) for feature extraction, neighborhood component analysis (NCA) for feature selection, and Support Vector Machine (SVM) for classification. The innovative inputs fed into the type-III fuzzy system come from the outputs of the mentioned neural networks. The system’s rule parameters are fine-tuned using the Improved Chaos Game Optimization algorithm (ICGO). The conventional CGO’s simple random mutation is substituted with wavelet mutation to enhance the CGO algorithm while preserving non-parametricity and computational complexity. The ICGO was evaluated using 126 benchmark functions and 5 engineering problems, comparing its performance with well-known algorithms. It achieved the best results across all functions except for 2 benchmark functions. The introduced classifier is applied to seven malware datasets and consistently outperforms notable networks like AlexNet, ResNet-18, GoogleNet, and Efficient Capsule neural network in 35 separate runs, achieving over 96% accuracy. Additionally, the classifier’s performance is tested on the MNIST and Fashion-MNIST in 10 separate runs. The results show that the new classifier excels in accuracy, precision, sensitivity, specificity, and F1-score compared to other recent classifiers. Based on the statistical analysis, it has been concluded that the ICGO and propose method exhibit significant superiority compared to the examined algorithms and methods. The source code for ICGO is available publicly at https://nimakhodadadi.com/algorithms-%2B-codes. Graphical abstract

show abstract

Breaking CAPTCHA with Capsule Networks

Cited by 6 publications

References 35 publications

Adaptive-CAPTCHA: A Text CAPTCHA Solver based on CRNN and Configurable Filter Networks

Adaptive-CAPTCHA: A Text CAPTCHA Solver based on CRNN and Configurable Filter Networks

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

Novel hybrid classifier based on fuzzy type-III decision maker and ensemble deep learning model and improved chaos game optimization

Contact Info

Product

Resources

About