Revisiting Text-Based CAPTCHAs: A Large-Scale Security and Usability Analysis Against CNN-Based Solvers
Author:
Open Access
- 12 November 2025
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 14 (22) , 4403
Abstract
Text-based CAPTCHAs remain a widely deployed mechanism for mitigating automated attacks across web platforms. However, the increasing effectiveness of convolutional neural networks (CNNs) and advanced computer vision models poses significant challenges to their reliability as a security measure. This study presents a comprehensive forensic and security-oriented analysis of text-based CAPTCHA systems, focusing on how individual and combined visual distortion features affect human usability and machine solvability. A real-world dataset comprising 45,166 CAPTCHA samples was generated under controlled conditions, integrating diverse anti-recognition, anti-segmentation, and anti-classification features. Recognition performance was systematically evaluated using both a CNN-based solver and actual human interaction data collected through an online exam platform. Results reveal that while traditional features such as warping and distortion still degrade machine accuracy to some extent, newer features like the hollow scheme and multi-layer structures offer better resistance against CNN-based attacks while maintaining human readability. Correlation and SHAP-based analyses were employed to quantify feature influence and identify configurations that optimize human–machine separability. This work contributes a publicly available dataset and a feature-impact framework, enabling deeper investigations into adversarial robustness, CAPTCHA resistance modeling, and security-aware human interaction systems. The findings underscore the need for adaptive CAPTCHA mechanisms that are both human-centric and resilient against evolving AI-based attacks.Keywords
This publication has 52 references indexed in Scilit:
- The influence of GNP on the mechanical and thermomechanical properties of epoxy adhesive: Pearson correlation matrix and heatmap application in data interpretationPolymer Composites, 2024
- Robustness and user test on text-based CAPTCHA: Letter segmenting is not too easy or too hardArray, 2024
- Practicality analysis of utilizing text-based CAPTCHA vs. graphic-based CAPTCHA authenticationMultimedia Tools and Applications, 2023
- Design of innovative CAPTCHA for hindi languageNeural Computing and Applications, 2022
- A cloud endpoint coordinating CAPTCHA based on multi-view stacking ensembleComputers & Security, 2021
- Is image-based CAPTCHA secure against attacks based on machine learning? An experimental studyComputers & Security, 2020
- CAPTCHA Design and Security Issues2018
- Cryptography Using Captcha Puzzles2013
- Building Segmentation Based Human-Friendly Human Interaction Proofs (HIPs)2005
- CAPTCHA: Using Hard AI Problems for Security2003