Enhancing the Security of Large Character Set CAPTCHAs Using Transferable Adversarial Examples
- 9 December 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (2) , 3898-3915
Abstract
The large character set CAPTCHA is an important extension of the traditional text-based CAPTCHA with larger alphabet languages to defend against automated attack programs. However, the state-of-the-art deep learning attacks have cracked such CAPTCHA. Existing defenses against such threats increase the complexity of CAPTCHA, thus decreasing usability. We propose ACG (Adversarial Large Character Set CAPTCHA Generation), a framework with two modules: a Fine-grained Generation Module, combining three novel strategies to prevent attackers from recognizing characters, and an Ensemble Generation Module to generate global perturbations in CAPTCHAs. It not only strengthens defense against recognition attacks but also improves robustness against diverse detection architectures through adversarial perturbations. Additionally, we develop a toolkit, Adv-Eval, consisting of CAPTCHA datasets from 10 of the most popular Chinese CAPTCHA schemes and benchmarking various attacks. We conduct extensive experiments using Adv-Eval to demonstrate ACG's efficacy, especially manifesting a significant decrease in the average success rate of diverse attacks from 51.52% to 2.56%. To the best of our knowledge, ACG is the first framework to defend large character set CAPTCHAs against detection attacks using transferable adversarial examples.Keywords
Funding Information
- Key Research and Development Program of Science and Technology Department of Sichuan Province (2023YFG0145)
- National Key Research and Development Program of China (2022YFC3303101)
This publication has 59 references indexed in Scilit:
- An efficient technique for breaking of coloured Hindi CAPTCHASoft Computing, 2023
- Robust Text CAPTCHAs Using Adversarial Examples2022
- Adaptive momentum variance for attention-guided sparse adversarial attacksPattern Recognition, 2022
- Design of innovative CAPTCHA for hindi languageNeural Computing and Applications, 2022
- A deep learning‐based attack on text CAPTCHAs by using object detection techniquesIET Information Security, 2021
- End-to-end attack on text-based CAPTCHAs based on cycle-consistent generative adversarial networkNeurocomputing, 2021
- Benchmarks for Designing a Secure Devanagari CAPTCHASN Computer Science, 2021
- Image‐based CAPTCHAs based on neural style transferIET Information Security, 2019
- ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector2019
- Chinese Character CAPTCHA Recognition and performance estimation via deep neural networkNeurocomputing, 2018