I Am 'Totally' Human: Bypassing the reCaptcha

S. S. Brown, Nicholas DiBari, Sajal Bhatia
{"title":"I Am 'Totally' Human: Bypassing the reCaptcha","authors":"S. S. Brown, Nicholas DiBari, Sajal Bhatia","doi":"10.1109/SITIS.2017.13","DOIUrl":null,"url":null,"abstract":"In recent years, website administrators have searched for a tool to prevent automated “bots” from using their sites' resources, hindering legitimate user access. By offering a “challenge” in the form of analyzing a picture for certain features, matching like symbols from a selection, or listening to an audio clip and transcribing the text, these tasks are intended to be easy for humans to solve but impossible for a program to overcome. More recently, there have been many successful attempts at using modern technology to automate passing these challenges. In this paper, we propose a simple approach which makes use of open-source tools (reCaptcha Widget, Selenium – a proxy server pool and a public Speech to Text API) to circumvent the reCaptcha tool utilized by Google. Preliminary results demonstrate an approximately 35% success rate which can be easily improved with minor modification. However, the focal point is the simplicity of the proposed approach to highlight the vulnerability of Google's reCaptcha tool against Speech to Text API attack.","PeriodicalId":153165,"journal":{"name":"2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SITIS.2017.13","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

Abstract

In recent years, website administrators have searched for a tool to prevent automated “bots” from using their sites' resources, hindering legitimate user access. By offering a “challenge” in the form of analyzing a picture for certain features, matching like symbols from a selection, or listening to an audio clip and transcribing the text, these tasks are intended to be easy for humans to solve but impossible for a program to overcome. More recently, there have been many successful attempts at using modern technology to automate passing these challenges. In this paper, we propose a simple approach which makes use of open-source tools (reCaptcha Widget, Selenium – a proxy server pool and a public Speech to Text API) to circumvent the reCaptcha tool utilized by Google. Preliminary results demonstrate an approximately 35% success rate which can be easily improved with minor modification. However, the focal point is the simplicity of the proposed approach to highlight the vulnerability of Google's reCaptcha tool against Speech to Text API attack.
我是“完全的”人类:绕过验证码
近年来,网站管理员一直在寻找一种工具,以防止自动“机器人”使用他们的网站资源,阻碍合法用户访问。通过提供“挑战”的形式来分析图片的某些特征,匹配选择中的符号,或者听音频片段并转录文本,这些任务对人类来说很容易解决,但对程序来说是不可能克服的。最近,已经有许多成功的尝试使用现代技术来自动通过这些挑战。在本文中,我们提出了一种简单的方法,利用开源工具(reCaptcha Widget, Selenium -代理服务器池和公共Speech to Text API)来绕过Google使用的reCaptcha工具。初步结果表明,成功率约为35%,可以很容易地提高,稍加修改。然而,重点是所提出的方法的简单性,以突出谷歌的reCaptcha工具对语音到文本API攻击的脆弱性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信