arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2308.08367cs.CRcs.CV
收藏

Diff-CAPTCHA:一种通过去噪扩散模型增强安全性的基于图像的 CAPTCHA

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

Southeast University(东南大学);Nanjing University of Posts and Telecommunications(南京邮电大学)

Ran Jiang, Sanfeng Zhang, Linfeng Liu, Yanbing Peng

AI总结:

本文提出基于去噪扩散模型的点选图像 CAPTCHA 方案 Diff-CAPTCHA,通过整体生成字符与背景削弱可学习特征,并经 Faster R-CNN 等攻击和三类基线对比验证其安全性与可用性。

摘要:

为了提升文本 CAPTCHA 的安全性,人们已经采用了多种方法,例如在文本上添加干扰线、随机扭曲字符以及重叠多个字符。这些方法在一定程度上增加了自动分割和识别攻击的难度。然而,面对端到端破解算法的快速发展,其安全性已被大幅削弱。扩散模型是一种新型图像生成模型,能够生成字符与背景图像深度融合的文本图像。本文基于去噪扩散模型提出了一种名为 Diff-CAPTCHA 的点选图像 CAPTCHA 方案。该方案将 CAPTCHA 的背景图像和字符视为一个整体,以引导扩散模型的生成过程,从而削弱可供机器学习利用的字符特征,增强 CAPTCHA 中字符特征的多样性,并提高破解算法的难度。为评估 Diff-CAPTCHA 的安全性,本文设计了多种攻击方法,包括基于 Faster R-CNN 的端到端攻击和两阶段攻击,并将 Diff-CAPTCHA 与三种基线方案进行比较,其中包括商业 CAPTCHA 方案和基于风格迁移的安全性增强 CAPTCHA 方案。实验结果表明,扩散模型能够有效增强 CAPTCHA 的安全性,同时在人工测试中保持良好的可用性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑