{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T15:20:01Z","timestamp":1787066401561,"version":"build-2736575974"},"reference-count":38,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T00:00:00Z","timestamp":1646870400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation","award":["SaTC-1936370, CICI-1917117, and SFS-1921485"],"award-info":[{"award-number":["SaTC-1936370, CICI-1917117, and SFS-1921485"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Manage. Inf. Syst."],"published-print":{"date-parts":[[2022,6,30]]},"abstract":"<jats:p>Automated monitoring of dark web (DW) platforms on a large scale is the first step toward developing proactive Cyber Threat Intelligence (CTI). While there are efficient methods for collecting data from the surface web, large-scale dark web data collection is often hindered by anti-crawling measures. In particular, text-based CAPTCHA serves as the most prevalent and prohibiting type of these measures in the dark web. Text-based CAPTCHA identifies and blocks automated crawlers by forcing the user to enter a combination of hard-to-recognize alphanumeric characters. In the dark web, CAPTCHA images are meticulously designed with additional background noise and variable character length to prevent automated CAPTCHA breaking. Existing automated CAPTCHA breaking methods have difficulties in overcoming these dark web challenges. As such, solving dark web text-based CAPTCHA has been relying heavily on human involvement, which is labor-intensive and time-consuming. In this study, we propose a novel framework for automated breaking of dark web CAPTCHA to facilitate dark web data collection. This framework encompasses a novel generative method to recognize dark web text-based CAPTCHA with noisy background and variable character length. To eliminate the need for human involvement, the proposed framework utilizes Generative Adversarial Network (GAN) to counteract dark web background noise and leverages an enhanced character segmentation algorithm to handle CAPTCHA images with variable character length. Our proposed framework, DW-GAN, was systematically evaluated on multiple dark web CAPTCHA testbeds. DW-GAN significantly outperformed the state-of-the-art benchmark methods on all datasets, achieving over 94.4% success rate on a carefully collected real-world dark web dataset. We further conducted a case study on an emergent Dark Net Marketplace (DNM) to demonstrate that DW-GAN eliminated human involvement by automatically solving CAPTCHA challenges with no more than three attempts. Our research enables the CTI community to develop advanced, large-scale dark web monitoring. We make DW-GAN code available to the community as an open-source tool in GitHub.<\/jats:p>","DOI":"10.1145\/3505226","type":"journal-article","created":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T09:05:52Z","timestamp":1646903152000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":31,"title":["Counteracting Dark Web Text-Based CAPTCHA with Generative Adversarial Learning for Proactive Cyber Threat Intelligence"],"prefix":"10.1145","volume":"13","author":[{"given":"Ning","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Arizona, Tucson, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1367-3338","authenticated-orcid":false,"given":"Mohammadreza","family":"Ebrahimi","sequence":"additional","affiliation":[{"name":"University of South Florida, Tampa, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weifeng","family":"Li","sequence":"additional","affiliation":[{"name":"University of Georgia, Athens, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hsinchun","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Arizona, Tucson, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,3,10]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/2046707.2046724"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-1557-2"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/6898617"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/2361256.2361257"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISI.2018.8587327"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.25300\/MISQ\/2022\/16618"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1080\/07421222.2020.1790186"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/SPW50608.2020.00021"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISI.2018.8587404"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-31321-0_35"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/2508859.2516732"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aag2612"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.5555\/3086952"},{"issue":"10","key":"e_1_3_2_15_2","first-page":"28","article-title":"Terror tech: New and innovative tools are being deployed in the ongoing fight against terrorism","volume":"63","author":"Heires Katherine","year":"2016","unstructured":"Katherine Heires. 2016. Terror tech: New and innovative tools are being deployed in the ongoing fight against terrorism. Risk Management 63, 10 (2016), 28\u201332.","journal-title":"Risk Management"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-4151-2"},{"key":"e_1_3_2_17_2","volume-title":"Proceedings of the 3rd International Conference on Learning Representations","author":"Kingma Diederik P.","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966298"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/2676869"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISI49825.2020.9280540"},{"key":"e_1_3_2_21_2","volume-title":"2017 Cybercrime Report","author":"Morgan Steve","year":"2017","unstructured":"Steve Morgan. 2017. 2017 Cybercrime Report. Technical Report. Cybersecurity Ventures. Retrieved 11 Feb., 2022 from http:\/\/www.cybersecurityventures.com\/hackerpocalypse-cybercrime-report-2016."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"e_1_3_2_23_2","article-title":"Deep-CAPTCHA: A deep learning based CAPTCHA solver for vulnerability assessment","author":"Nouri Zahra","year":"2020","unstructured":"Zahra Nouri and Mahdi Rezaei. 2020. Deep-CAPTCHA: A deep learning based CAPTCHA solver for vulnerability assessment. Available at SSRN 3633354 (2020). Accessed 11 Feb., 2022.","journal-title":"Available at SSRN 3633354"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3382158"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2014.2321001"},{"issue":"3","key":"e_1_3_2_26_2","article-title":"Algorithm border tracing vs scanline in blob detection for robot soccer vision system.","volume":"11","author":"Pratomo Awang Hendrianto","year":"2019","unstructured":"Awang Hendrianto Pratomo, Anggit Ferdita Nugraha, Joko Siswantoro, and Mohammad Faidzul Nasruddin. 2019. Algorithm border tracing vs scanline in blob detection for robot soccer vision system. International Journal of Advances in Soft Computing & Its Applications 11, 3 (2019), 40\u201356.","journal-title":"International Journal of Advances in Soft Computing & Its Applications"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.5555\/3103282"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1080\/07421222.2017.1394049"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3191528"},{"key":"e_1_3_2_30_2","volume-title":"Deep Learning for Computer Vision: Expert Techniques to Train Advanced Neural Networks using TensorFlow and Keras","author":"Shanmugamani Rajalingappaa","year":"2018","unstructured":"Rajalingappaa Shanmugamani. 2018. Deep Learning for Computer Vision: Expert Techniques to Train Advanced Neural Networks using TensorFlow and Keras. Packt Publishing Ltd."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2821096"},{"key":"e_1_3_2_32_2","unstructured":"Claire Tsosie. [n.d.]. Discover Launches Social Security Number Alert Features. Retrieved from https:\/\/www.nerdwallet.com\/article\/credit-cards\/discover-feature-alerts-social-security-number-risky-sites-dark-web. (2020\/07\/21)."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3386243"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3460823"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.26599\/BDMA.2019.9020001"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-018-1342-8"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.26483\/ijarcs.v9i2.5868"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243754"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TrustCom\/BigDataSE.2019.00020"}],"container-title":["ACM Transactions on Management Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3505226","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3505226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T15:31:26Z","timestamp":1750174286000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3505226"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,10]]},"references-count":38,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,6,30]]}},"alternative-id":["10.1145\/3505226"],"URL":"https:\/\/doi.org\/10.1145\/3505226","relation":{},"ISSN":["2158-656X","2158-6578"],"issn-type":[{"value":"2158-656X","type":"print"},{"value":"2158-6578","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,10]]},"assertion":[{"value":"2020-11-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-12-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-03-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}