Diff-CAPTCHA: An Image-based CAPTCHA with Security Enhanced by Denoising Diffusion Model

by   Ran Jiang, et al.

To enhance the security of text CAPTCHAs, various methods have been employed, such as adding the interference lines on the text, randomly distorting the characters, and overlapping multiple characters. These methods partly increase the difficulty of automated segmentation and recognition attacks. However, facing the rapid development of the end-to-end breaking algorithms, their security has been greatly weakened. The diffusion model is a novel image generation model that can generate the text images with deep fusion of characters and background images. In this paper, an image-click CAPTCHA scheme called Diff-CAPTCHA is proposed based on denoising diffusion models. The background image and characters of the CAPTCHA are treated as a whole to guide the generation process of a diffusion model, thus weakening the character features available for machine learning, enhancing the diversity of character features in the CAPTCHA, and increasing the difficulty of breaking algorithms. To evaluate the security of Diff-CAPTCHA, this paper develops several attack methods, including end-to-end attacks based on Faster R-CNN and two-stage attacks, and Diff-CAPTCHA is compared with three baseline schemes, including commercial CAPTCHA scheme and security-enhanced CAPTCHA scheme based on style transfer. The experimental results show that diffusion models can effectively enhance CAPTCHA security while maintaining good usability in human testing.


page 5

page 7

page 10

page 11

page 14

page 16

page 19


Nested Diffusion Processes for Anytime Image Generation

Diffusion models are the current state-of-the-art in image generation, s...

A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion

Despite the record-breaking performance in Text-to-Image (T2I) generatio...

Counteracting Dark Web Text-Based CAPTCHA with Generative Adversarial Learning for Proactive Cyber Threat Intelligence

Automated monitoring of dark web (DW) platforms on a large scale is the ...

Intriguing Properties of Diffusion Models: A Large-Scale Dataset for Evaluating Natural Attack Capability in Text-to-Image Generative Models

Denoising probabilistic diffusion models have shown breakthrough perform...

Adversarial CAPTCHAs

Following the principle of to set one's own spear against one's own shie...

PAI-Diffusion: Constructing and Serving a Family of Open Chinese Diffusion Models for Text-to-image Synthesis on the Cloud

Text-to-image synthesis for the Chinese language poses unique challenges...

DiffWA: Diffusion Models for Watermark Attack

With the rapid development of deep neural networks(DNNs), many robust bl...

Please sign up or login with your details

Forgot password? Click here to reset