Robust CAPTCHA Image Generation Enhanced with Adversarial Example Methods
Robust CAPTCHA Image Generation Enhanced with Adversarial Example Methods
复制标题
DOI：
10.1587/transinf.2019edl8194
复制
发表时间：
2020-04-01
影响因子：
0.7
通讯作者：
Park, Ki-Woong
中科院分区：
文献类型：
--
作者：
Kwon, Hyun;Yoon, Hyunsoo;Park, Ki-Woong
互联网上的恶意攻击者使用自动攻击程序，通过大量垃圾邮件、不必要的公告板和创建帐户来破坏服务的使用。完全自动化的区分计算机和人类的公共图灵测试（CAPTCHA）被用作防止此类自动攻击的安全解决方案。验证码是一种通过提供只有人类才能理解的扭曲字母、声音和图像来确定用户是机器还是人的系统。然而，光学字符识别（OCR）和深度神经网络（DNN）等新的攻击技术已被用来绕过验证码。在本文中，我们提出了一种使用快速梯度符号方法（FGSM）、迭代FGSM（I-FGSM）和DeepFool方法来生成验证码图像的方法。我们使用python提供的验证码图像作为数据集，使用Tensorflow作为机器学习库。实验结果表明，通过FGSM、I-FGSM和DeepFool方法生成的验证码图像，FGSM在epsilon = 0.15时识别率为0%，I-FGSM在alpha = 0.1时50次迭代时识别率为0%，而DeepFool方法在150次迭代时识别率为45%。
Malicious attackers on the Internet use automated attack programs to disrupt the use of services via mass spamming, unnecessary bulletin boarding, and account creation. Completely automated public turing test to tell computers and humans apart (CAPTCHA) is used as a security solution to prevent such automated attacks. CAPTCHA is a system that determines whether the user is a machine or a person by providing distorted letters, voices, and images that only humans can understand. However, new attack techniques such as optical character recognition (OCR) and deep neural networks (DNN) have been used to bypass CAPTCHA. In this paper, we propose a method to generate CAPTCHA images by using the fast-gradient sign method (FGSM), iterative FGSM (I-FGSM), and the DeepFool method. We used the CAPTCHA image provided by python as the dataset and Tensorflow as the machine learning library. The experimental results show that the CAPTCHA image generated via FGSM, I-FGSM, and DeepFool methods exhibits a 0% recognition rate with epsilon = 0.15 for FGSM, a 0% recognition rate with alpha = 0.1 with 50 iterations for I-FGSM, and a 45% recognition rate with 150 iterations for the DeepFool method.