{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T02:43:49Z","timestamp":1747190629678,"version":"3.40.5"},"reference-count":35,"publisher":"Wiley","license":[{"start":{"date-parts":[[2021,6,15]],"date-time":"2021-06-15T00:00:00Z","timestamp":1623715200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Security and Communication Networks"],"published-print":{"date-parts":[[2021,6,15]]},"abstract":"<jats:p>In the past decades, due to the low design cost and easy maintenance, text-based CAPTCHAs have been extensively used in constructing security mechanisms for user authentications. With the recent advances in machine\/deep learning in recognizing CAPTCHA images, growing attack methods are presented to break text-based CAPTCHAs. These machine learning\/deep learning-based attacks often rely on training models on massive volumes of training data. The poorly constructed CAPTCHA data also leads to low accuracy of attacks. To investigate this issue, we propose a simple, generic, and effective preprocessing approach to filter and enhance the original CAPTCHA data set so as to improve the accuracy of the previous attack methods. In particular, the proposed preprocessing approach consists of a data selector and a data augmentor. The data selector can automatically filter out a training data set with training significance. Meanwhile, the data augmentor uses four different image noises to generate different CAPTCHA images. The well-constructed CAPTCHA data set can better train deep learning models to further improve the accuracy rate. Extensive experiments demonstrate that the accuracy rates of five commonly used attack methods after combining our preprocessing approach are 2.62% to 8.31% higher than those without preprocessing approach. Moreover, we also discuss potential research directions for future work.<\/jats:p>","DOI":"10.1155\/2021\/9930608","type":"journal-article","created":{"date-parts":[[2021,6,16]],"date-time":"2021-06-16T20:05:05Z","timestamp":1623873905000},"page":"1-9","source":"Crossref","is-referenced-by-count":4,"title":["Augmented Data Selector to Initiate Text-Based CAPTCHA Attack"],"prefix":"10.1155","volume":"2021","author":[{"given":"Aolin","family":"Che","sequence":"first","affiliation":[{"name":"Macau University of Science and Technology, Macau, China"}]},{"given":"Yalin","family":"Liu","sequence":"additional","affiliation":[{"name":"Macau University of Science and Technology, Macau, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0823-0877","authenticated-orcid":true,"given":"Hong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology, Guangzhou 510006, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9301-5989","authenticated-orcid":true,"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science in Norwegian University of Science and Technology, Gj\u00f8vik, Norway"}]},{"given":"Ke","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6165-4196","authenticated-orcid":true,"given":"Hong-Ning","family":"Dai","sequence":"additional","affiliation":[{"name":"Macau University of Science and Technology, Macau, China"}]}],"member":"311","reference":[{"first-page":"294","article-title":"CAPTCHA: using hard AI problems for security","author":"L. Von Ahn","key":"1"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1160379"},{"first-page":"3","article-title":"Re: captchas-understanding captcha-solving services in an economic context","author":"M. Motoyama","key":"3"},{"first-page":"995","article-title":"Captcha for blind people","author":"M. Shirali-Shahreza","key":"4"},{"first-page":"2267","article-title":"The soundsright captcha: an improved approach to audio human interaction proofs for blind users","author":"J. Lazar","key":"5"},{"issue":"2","key":"6","first-page":"2242","article-title":"Survey of different types of captcha","volume":"5","author":"V. P. Singh","year":"2014","journal-title":"International Journal of Computer Science and Information Technologies"},{"first-page":"332","article-title":"Yet another text captcha solver: a generative adversarial network based approach","author":"G. Ye","key":"7"},{"first-page":"860","article-title":"A generic solver combining unsupervised learning and representation learning for breaking text-based captchas","author":"S. Tian","key":"8"},{"first-page":"1","article-title":"Breaking captcha characters using multi-task learning cnn and svm","author":"S. Sachdev","key":"9"},{"first-page":"1075","article-title":"The robustness of hollow captchas","author":"H. Gao","key":"10"},{"first-page":"543","article-title":"A low-cost attack on a microsoft captcha","author":"J. Yan","key":"11"},{"first-page":"770","article-title":"Deep residual learning for image recognition","author":"K. He","key":"12"},{"article-title":"Multi-digit number recognition from street view imagery using deep convolutional neural networks","year":"2013","author":"I. J. Goodfellow","key":"13"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/access.2014.2325029"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-014-0007-7"},{"first-page":"442","article-title":"Under-optimized smart contracts devour your money","author":"T. Chen","key":"16"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1145\/3381036"},{"first-page":"125","article-title":"Text-based captcha strengths and weaknesses","author":"E. Bursztein","key":"18"},{"first-page":"1503","article-title":"Tokenscope: automatically detecting inconsistent behaviors of cryptocurrency tokens in ethereum","author":"T. Chen","key":"19"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2019.2898174"},{"issue":"8","key":"21","doi-asserted-by":"crossref","first-page":"5790","DOI":"10.1109\/TII.2020.3047675","article-title":"Siamese neural network based few-shot learning for anomaly detection in industrial cyber-physical systems","volume":"17","author":"X. Zhou","year":"2020","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"5","key":"22","doi-asserted-by":"crossref","first-page":"3322","DOI":"10.1109\/TII.2019.2953289","article-title":"Energy-aware green adversary model for cyberphysical security in industrial system","volume":"16","author":"A. K. Sangaiah","year":"2019","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3053842"},{"key":"24","article-title":"Energy-aware geographic routing for real time workforce monitoring in industrial informatics","author":"A. K. Sangaiah","year":"2021","journal-title":"IEEE Internet of Things Journal"},{"issue":"5","key":"25","doi-asserted-by":"crossref","first-page":"3469","DOI":"10.1109\/TII.2020.3022432","article-title":"Variational lstm enhanced anomaly detection for industrial big data","volume":"17","author":"X. Zhou","year":"2020","journal-title":"IEEE Transactions on Industrial Informatics"},{"author":"G. Mori","key":"26","article-title":"Recognizing objects in adversarial clutter: breaking a visual captcha"},{"key":"27","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1109\/TIFS.2019.2928622","article-title":"An end-to-end attack on text captchas","volume":"15","author":"Y. Zi","year":"2019","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2018.07.155"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1109\/tifs.2018.2821096"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2020.101947"},{"author":"J. Yan","key":"31","article-title":"A simple generic attack on text captchas"},{"key":"32","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"K. Simonyan","key":"33"},{"first-page":"44","article-title":"Usability of captchas or usability issues in captcha design","author":"J. Yan","key":"34"},{"first-page":"2623","article-title":"On the necessity of user-friendly captcha","author":"C. A. Fidas","key":"35"}],"container-title":["Security and Communication Networks"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/scn\/2021\/9930608.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/scn\/2021\/9930608.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/scn\/2021\/9930608.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,16]],"date-time":"2021-06-16T20:05:10Z","timestamp":1623873910000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/scn\/2021\/9930608\/"}},"subtitle":[],"editor":[{"given":"Ting","family":"Chen","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,6,15]]},"references-count":35,"alternative-id":["9930608","9930608"],"URL":"https:\/\/doi.org\/10.1155\/2021\/9930608","relation":{},"ISSN":["1939-0122","1939-0114"],"issn-type":[{"type":"electronic","value":"1939-0122"},{"type":"print","value":"1939-0114"}],"subject":[],"published":{"date-parts":[[2021,6,15]]}}}