Style Transfer and Topological Feature Analysis of Text-Based CAPTCHA via Generative Adversarial Networks

The design and cracking of text-based CAPTCHAs are important topics in computer security. This study proposes a method for the style transfer of text-based CAPTCHAs using Generative Adversarial Networks (GANs). First, a curated dataset was used, combining a text-based CAPTCHA library and image collections from four artistic styles—Van Gogh, Monet, Cézanne, and Ukiyo-e—which were used to generate style-based text CAPTCHA samples. Subsequently, a universal style transfer model, along with trained CycleGAN models for both single- and double-style transfers, were employed to generate style-enhanced text-based CAPTCHAs. Traditional methods for evaluating the anti-recognition capability of text-based CAPTCHAs primarily focus on recognition success rates. This study introduces topological feature analysis as a new method for evaluating text-based CAPTCHAs. Initially, the recognition success rates of the three methods across four styles were evaluated using Muggle-OCR. Subsequently, the graph diameter was employed to quantify the differences between text-based CAPTCHA images before and after style transfer. The experimental results demonstrate that the recognition rates of style-enhanced text-based CAPTCHAs are consistently lower than those of the original CAPTCHA, suggesting that style transfer enhances anti-recognition capability. Topological feature analysis indicates that style transfer results in a more compact topological structure, further validating the effectiveness of the GAN-based twice-transfer method in enhancing CAPTCHA complexity and anti-recognition capability.