Title: Security analysis of image CAPTCHA using a mask R-CNN-based attack model

Authors: Vijaypal Singh Rathor; Bharat Garg; Mandar Patil; G.K. Sharma

Addresses: Bennett University, Greater Noida, India ' Thapar Institute of Engineering and Technology, Patiala, India ' ABV – Indian Institute of Information Technology and Management, Gwalior 474015, India ' ABV – Indian Institute of Information Technology and Management, Gwalior 474015, India

Abstract: The CAPTCHAs are attacked by automated programs to break their underlying design principle. Therefore, analysing the robustness of CAPTCHA is the critical requirement. Recently, a neural style transfer-based image CAPTCHA called style area CAPTCHA (SACAPTCHA) has been reported. Though the security of SACAPTCHA is evaluated on R-CNN and FCN attack models using accuracy metrics, they are ineffective to analyse its robustness. Therefore, we propose a mask R-CNN-based attack model to critically analyse the robustness of SACAPTCHA. The proposed model performs a shape-wise analysis to test the usability of different shapes and quantifies the model performance using the F1-score. The simulation results show the highest F1 score of 0.962 and 0.828 for star and circle shapes in dataset-1 and dataset-2 respectively. The results show that model prediction is independent of the regularities of the shape. The observations prove that SACAPTCHA is vulnerable to object detection attack even after using irregular shapes.

Keywords: image CAPTCHA; object detection; convolution neural network; security; deep learning.

DOI: 10.1504/IJAHUC.2021.114108

International Journal of Ad Hoc and Ubiquitous Computing, 2021 Vol.36 No.4, pp.238 - 247

Received: 13 May 2020
Accepted: 09 Dec 2020
Published online: 08 Apr 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article