基于阿拉伯语文本的人类CAPTCHA难度参数化研究

IF 2 4区计算机科学 Q2 Computer Science

Intelligent Automation and Soft Computing Pub Date : 2022-01-01 DOI:10.32604/IASC.2022.019913

Suliman A. Alsuhibany, Hessah Abdulaziz Alhodathi

{"title":"基于阿拉伯语文本的人类CAPTCHA难度参数化研究","authors":"Suliman A. Alsuhibany, Hessah Abdulaziz Alhodathi","doi":"10.32604/IASC.2022.019913","DOIUrl":null,"url":null,"abstract":"The Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA) technique has been an interesting topic for several years. An Arabic CAPTCHA has recently been proposed to serve Arab users. Since there have been few scientific studies supporting a systematic design or tuning for users, this paper aims to analyze the Arabic text-based CAPTCHA at the parameter level by conducting an experimental study. Based on the results of this study, we propose an Arabic text-based CAPTCHA scheme with Fast Gradient Sign Method (FGSM) adversarial images. To evaluate the security of the proposed scheme, we ran four filter attacks, which led to a success rate of less than 5%. Thus, we developed a defensive method against adaptive attacks which is a standard for evaluating defenses to adversarial examples. This method is ensemble adversarial training, and it gave an accuracy result of 41.51%. For the usability aspect, we conducted an experimental study, and the results showed that it can be solved by humans in a few seconds with a success rate of 93.10%.","PeriodicalId":50357,"journal":{"name":"Intelligent Automation and Soft Computing","volume":"31 1","pages":"523-537"},"PeriodicalIF":2.0000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"A Parametric Study of Arabic Text-Based CAPTCHA Difficulty for Humans\",\"authors\":\"Suliman A. Alsuhibany, Hessah Abdulaziz Alhodathi\",\"doi\":\"10.32604/IASC.2022.019913\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA) technique has been an interesting topic for several years. An Arabic CAPTCHA has recently been proposed to serve Arab users. Since there have been few scientific studies supporting a systematic design or tuning for users, this paper aims to analyze the Arabic text-based CAPTCHA at the parameter level by conducting an experimental study. Based on the results of this study, we propose an Arabic text-based CAPTCHA scheme with Fast Gradient Sign Method (FGSM) adversarial images. To evaluate the security of the proposed scheme, we ran four filter attacks, which led to a success rate of less than 5%. Thus, we developed a defensive method against adaptive attacks which is a standard for evaluating defenses to adversarial examples. This method is ensemble adversarial training, and it gave an accuracy result of 41.51%. For the usability aspect, we conducted an experimental study, and the results showed that it can be solved by humans in a few seconds with a success rate of 93.10%.\",\"PeriodicalId\":50357,\"journal\":{\"name\":\"Intelligent Automation and Soft Computing\",\"volume\":\"31 1\",\"pages\":\"523-537\"},\"PeriodicalIF\":2.0000,\"publicationDate\":\"2022-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Intelligent Automation and Soft Computing\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.32604/IASC.2022.019913\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"Computer Science\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Intelligent Automation and Soft Computing","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.32604/IASC.2022.019913","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Computer Science","Score":null,"Total":0}

引用次数: 1

摘要

完全自动化公共图灵测试来区分计算机和人类(CAPTCHA)技术已经成为一个有趣的话题好几年了。阿拉伯语验证码最近被提议为阿拉伯用户提供服务。由于很少有科学研究支持对用户进行系统设计或调优，因此本文旨在通过实验研究，在参数层面对基于阿拉伯语文本的CAPTCHA进行分析。基于本研究的结果，我们提出了一种基于阿拉伯语文本的快速梯度签名方法(FGSM)对抗图像的验证码方案。为了评估所提出方案的安全性，我们运行了四次过滤器攻击，成功率小于5%。因此，我们开发了一种针对自适应攻击的防御方法，这是评估对抗性示例防御的标准。该方法为集合对抗训练，准确率达到41.51%。在可用性方面，我们进行了实验研究，结果表明，人类可以在几秒钟内解决，成功率为93.10%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A Parametric Study of Arabic Text-Based CAPTCHA Difficulty for Humans

The Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA) technique has been an interesting topic for several years. An Arabic CAPTCHA has recently been proposed to serve Arab users. Since there have been few scientific studies supporting a systematic design or tuning for users, this paper aims to analyze the Arabic text-based CAPTCHA at the parameter level by conducting an experimental study. Based on the results of this study, we propose an Arabic text-based CAPTCHA scheme with Fast Gradient Sign Method (FGSM) adversarial images. To evaluate the security of the proposed scheme, we ran four filter attacks, which led to a success rate of less than 5%. Thus, we developed a defensive method against adaptive attacks which is a standard for evaluating defenses to adversarial examples. This method is ensemble adversarial training, and it gave an accuracy result of 41.51%. For the usability aspect, we conducted an experimental study, and the results showed that it can be solved by humans in a few seconds with a success rate of 93.10%.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Intelligent Automation and Soft Computing 工程技术-计算机：人工智能

CiteScore

3.50

自引率

10.00%

发文量

429

审稿时长

10.8 months

期刊介绍： An International Journal seeks to provide a common forum for the dissemination of accurate results about the world of intelligent automation, artificial intelligence, computer science, control, intelligent data science, modeling and systems engineering. It is intended that the articles published in the journal will encompass both the short and the long term effects of soft computing and other related fields such as robotics, control, computer, vision, speech recognition, pattern recognition, data mining, big data, data analytics, machine intelligence, cyber security and deep learning. It further hopes it will address the existing and emerging relationships between automation, systems engineering, system of systems engineering and soft computing. The journal will publish original and survey papers on artificial intelligence, intelligent automation and computer engineering with an emphasis on current and potential applications of soft computing. It will have a broad interest in all engineering disciplines, computer science, and related technological fields such as medicine, biology operations research, technology management, agriculture and information technology.