Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Classifying Google reCAPTCHA v2 - A study using transfer learning models and evaluating their robustness against adversarial perturbations

Björklund, Arvid LU and Uogele, Marius LU (2023) DABN01 20231
Department of Statistics
Department of Economics
Abstract
This thesis seeks to examine the suitability and robustness of transfer learning models in creating an efficient reCAPTCHA v2 classifier, and further evaluates their performance against various adversarial attacks. Three models - DenseNet201, EfficientNetV2, and InceptionV3 - were trained and assessed, highlighting the applicability of transfer learning techniques in the classification of reCAPTCHA v2 challenges. Despite variation in performance metrics, all models achieved satisfactory results, with DenseNet201 outperforming others in validation and test accuracy, and InceptionV3 demonstrating shortest training time.

The paper additionally showed varying levels of robustness for several different adversarial attacks among the models,... (More)
This thesis seeks to examine the suitability and robustness of transfer learning models in creating an efficient reCAPTCHA v2 classifier, and further evaluates their performance against various adversarial attacks. Three models - DenseNet201, EfficientNetV2, and InceptionV3 - were trained and assessed, highlighting the applicability of transfer learning techniques in the classification of reCAPTCHA v2 challenges. Despite variation in performance metrics, all models achieved satisfactory results, with DenseNet201 outperforming others in validation and test accuracy, and InceptionV3 demonstrating shortest training time.

The paper additionally showed varying levels of robustness for several different adversarial attacks among the models, with EfficientNetV2 proving to be the most resilient. This variability, despite identical top layers, points to the underlying base architecture as a significant determinant of a model's robustness against adversarial attacks. Consequently, the study supports a comprehensive evaluation for model selection, considering not only the performance of metrics but also the underlying model’s architectural properties that may affect its robustness.

Finally, this work indicates the potential of transfer learning models for image-based CAPTCHA challenge classification and stresses the need for further research focusing on enhancing the adversarial robustness of these models. The findings of this study contribute to the expanding body of research on transfer learning, showcasing its potential applications in the domain of image-based CAPTCHA systems. (Less)
Please use this url to cite or link to this publication:
author
Björklund, Arvid LU and Uogele, Marius LU
supervisor
organization
course
DABN01 20231
year
type
H1 - Master's Degree (One Year)
subject
keywords
reCAPTCHA, transfer learning, adversarial perturbations, convolutional neural network
language
English
id
9121132
date added to LUP
2023-11-21 12:53:40
date last changed
2023-11-21 12:53:40
@misc{9121132,
  abstract     = {{This thesis seeks to examine the suitability and robustness of transfer learning models in creating an efficient reCAPTCHA v2 classifier, and further evaluates their performance against various adversarial attacks. Three models - DenseNet201, EfficientNetV2, and InceptionV3 - were trained and assessed, highlighting the applicability of transfer learning techniques in the classification of reCAPTCHA v2 challenges. Despite variation in performance metrics, all models achieved satisfactory results, with DenseNet201 outperforming others in validation and test accuracy, and InceptionV3 demonstrating shortest training time.

The paper additionally showed varying levels of robustness for several different adversarial attacks among the models, with EfficientNetV2 proving to be the most resilient. This variability, despite identical top layers, points to the underlying base architecture as a significant determinant of a model's robustness against adversarial attacks. Consequently, the study supports a comprehensive evaluation for model selection, considering not only the performance of metrics but also the underlying model’s architectural properties that may affect its robustness.

Finally, this work indicates the potential of transfer learning models for image-based CAPTCHA challenge classification and stresses the need for further research focusing on enhancing the adversarial robustness of these models. The findings of this study contribute to the expanding body of research on transfer learning, showcasing its potential applications in the domain of image-based CAPTCHA systems.}},
  author       = {{Björklund, Arvid and Uogele, Marius}},
  language     = {{eng}},
  note         = {{Student Paper}},
  title        = {{Classifying Google reCAPTCHA v2 - A study using transfer learning models and evaluating their robustness against adversarial perturbations}},
  year         = {{2023}},
}