{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:25:04Z","timestamp":1772119504731,"version":"3.50.1"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Inf. Secur."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s10207-024-00950-9","type":"journal-article","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T01:11:39Z","timestamp":1733101899000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An intrinsic evaluator for embedding methods in malicious URL detection"],"prefix":"10.1007","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4309-843X","authenticated-orcid":false,"given":"Qisheng","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1371-4454","authenticated-orcid":false,"given":"Kazumasa","family":"Omote","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"950_CR1","doi-asserted-by":"crossref","unstructured":"Chen,Q., Omote,K.: Toward the establishment of evaluating URL embedding methods using intrinsic evaluator via malicious URLs detection. In: 38TH International Conference on ICT Systems Security and Privacy Protection (IFIP SEC), pp. 350\u2013360 (2023)","DOI":"10.1007\/978-3-031-56326-3_25"},{"key":"950_CR2","unstructured":"Goldberg,Y., Levy, O.: word2vec explained: deriving Mikolov et al.\u2019s negative-sampling word-embedding method, CoRR abs\/1402.3722 (2014). http:\/\/arxiv.org\/abs\/1402.3722"},{"key":"950_CR3","unstructured":"Joulin, A., Grave, E., Bojanowski, P., Douze, M., J\u00e9gou, H., Mikolov, T.: Fasttext. zip: compressing text classification models, arXiv preprint arXiv:1612.03651 (2016)"},{"key":"950_CR4","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2014), pp. 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"950_CR5","doi-asserted-by":"publisher","unstructured":"Rajaraman, A., Ullman, J.D.: Data mining, Cambridge University Press (2011), pp. 1\u201317. https:\/\/doi.org\/10.1017\/CBO9781139058452.002","DOI":"10.1017\/CBO9781139058452.002"},{"key":"950_CR6","doi-asserted-by":"crossref","unstructured":"Pradeepa, G., Devi, R.: Review of malicious URL detection using machine learning. In: Soft Computing for Security Applications, pp 97\u2013105, Springer (2022)","DOI":"10.1007\/978-981-16-5301-8_7"},{"key":"950_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Q., Omote, K.: A three-step framework for detecting malicious URLs. In: 2022 International Symposium on Networks, Computers and Communications (ISNCC), IEEE, pp. 1\u20136 (2022)","DOI":"10.1109\/ISNCC55209.2022.9851734"},{"key":"950_CR8","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2019.12","volume":"8","author":"B Wang","year":"2019","unstructured":"Wang, B., Wang, A., Chen, F., Wang, Y., Kuo, C.C.J.: Evaluating word embedding models: methods and experimental results. APSIPA Trans Signal Inform Process 8, e19 (2019)","journal-title":"APSIPA Trans Signal Inform Process"},{"key":"950_CR9","doi-asserted-by":"publisher","unstructured":"Yuan, H., Yang, Z., Chen, X., Li, Y., Liu, W.: URL2Vec: URL modeling with character embeddings for fast and accurate phishing website detection. In: 2018 ISPA\/IUCC\/BDCloud\/SocialCom\/SustainCom (2018), pp. 265\u2013272. https:\/\/doi.org\/10.1109\/BDCloud.2018.00050","DOI":"10.1109\/BDCloud.2018.00050"},{"key":"950_CR10","volume-title":"Innovative Security Solutions for Information Technology and Communications","author":"S Kaneko","year":"2020","unstructured":"Kaneko, S., Yamada, A., Sawaya, Y., Thao, T.P., Kubota, A., Omote, K.: Detecting malicious websites by query templates. In: Simion, E., G\u00e9raud-Stewart, R. (eds.) Innovative Security Solutions for Information Technology and Communications. Springer, New York (2020)"},{"key":"950_CR11","unstructured":"Le, H., Pham, Q., Sahoo, D., Hoi, S.C.H.: URLNet: learning a URL representation with deep learning for malicious URL detection, CoRR abs\/1802.03162 (2018)"},{"key":"950_CR12","unstructured":"Saxe, J., Berlin, K.: eXpose: a character-level convolutional neural network with embeddings for detecting malicious URLs, file paths and registryb keys, arXiv preprint arXiv:1702.08568 (2017)"},{"issue":"10","key":"950_CR13","doi-asserted-by":"publisher","first-page":"6673","DOI":"10.1109\/TII.2020.2977886","volume":"16","author":"X Yan","year":"2020","unstructured":"Yan, X., Xu, Y., Cui, B., Zhang, S., Guo, T., Li, C.: Learning URL embedding for malicious website detection. IEEE Trans. Ind. Inform. 16(10), 6673 (2020)","journal-title":"IEEE Trans. Ind. Inform."},{"key":"950_CR14","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1016\/j.eswa.2018.09.029","volume":"117","author":"OK Sahingoz","year":"2019","unstructured":"Sahingoz, O.K., Buber, E., Demir, O., Diri, B.: Machine learning based phishing detection from URLs. Expert Syst. Appl. 117, 345 (2019)","journal-title":"Expert Syst. Appl."},{"issue":"1","key":"950_CR15","first-page":"1","volume":"11","author":"C Do Xuan","year":"2020","unstructured":"Do Xuan, C., Nguyen, H.D., Nikolaevich, T.V., et al.: Malicious URL detection based on machine learning. Int. J. Adv. Comput. Sci. Appl. 11(1), 1 (2020)","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"950_CR16","doi-asserted-by":"crossref","unstructured":"Patgiri, R., Katari, H., Kumar, R., Sharma, D.: Empirical study on malicious URL detection using machine learning. In: International Conference on Distributed Computing and Internet Technology, pp. 380\u2013388, Springer (2019)","DOI":"10.1007\/978-3-030-05366-6_31"},{"key":"950_CR17","doi-asserted-by":"crossref","unstructured":"Djaballah, K.A., Boukhalfa, K., Ghalem, Z., Boukerma, O.: A new approach for the detection and analysis of phishing in social networks: the case of Twitter. In: 2020 Seventh International Conference on Social Networks Analysis, Management and Security, IEEE, pp. 1\u20138 (2020)","DOI":"10.1109\/SNAMS52053.2020.9336572"},{"key":"950_CR18","doi-asserted-by":"crossref","unstructured":"Kumar,Y., Subba,B.: A lightweight machine learning based security framework for detecting phishing attacks. In: 2021 International Conference on Communication Systems & Networks, IEEE, pp. 184\u2013188 (2021)","DOI":"10.1109\/COMSNETS51098.2021.9352828"},{"issue":"2","key":"950_CR19","first-page":"141","volume":"10","author":"D Patil","year":"2018","unstructured":"Patil, D., Patil, J.: Feature-based malicious URL and attack type detection using multi-class classification. ISC Int. J. Inform. Secur. 10(2), 141 (2018)","journal-title":"ISC Int. J. Inform. Secur."},{"key":"950_CR20","doi-asserted-by":"crossref","unstructured":"Zamir, A., Khan, H.U., Iqbal, T., Yousaf, N., Aslam, F., Anjum, A., Hamdani, M.: Phishing web site detection using diverse machine learning algorithms, The Electronic Library (2020)","DOI":"10.1108\/EL-05-2019-0118"},{"key":"950_CR21","doi-asserted-by":"crossref","unstructured":"Catak, F., Ozgur, K., Sahinbas, D\u00f6rtkarde\u015f, V.: Malicious URL detection using machine learning. In: Artificial Intelligence Paradigms for Smart Cyber-Physical Systems, IGI Global, pp. 160\u2013180 (2021)","DOI":"10.4018\/978-1-7998-5101-1.ch008"},{"key":"950_CR22","doi-asserted-by":"crossref","unstructured":"Alam, M.N., Sarma, D., Lima, F.F., Saha, I., Hossain, S., et\u00a0al.: Phishing attacks detection using machine learning approach. In: 2020 Third International Conference on Smart Systems and Inventive Technology, IEEE, pp. 1173\u20131179 (2020)","DOI":"10.1109\/ICSSIT48917.2020.9214225"},{"key":"950_CR23","doi-asserted-by":"publisher","unstructured":"Ho, T.K.: Random decision forests. In: Proceedings of 3rd International Conference on Document Analysis and Recognition, vol.\u00a01 (1995), vol.\u00a01, pp. 278\u2013282. https:\/\/doi.org\/10.1109\/ICDAR.1995.598994","DOI":"10.1109\/ICDAR.1995.598994"},{"key":"950_CR24","first-page":"3146","volume":"30","author":"G Ke","year":"2017","unstructured":"Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., Liu, T.Y.: Lightgbm: a highly efficient gradient boosting decision tree. Adv. Neural Inform. Process. Syst. 30, 3146 (2017)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"950_CR25","unstructured":"Top sites\u2014alexa. https:\/\/www.alexa.com\/topsites"},{"key":"950_CR26","unstructured":"Urlhaus | malware URL exchange. https:\/\/urlhaus.abuse.ch\/"}],"updated-by":[{"DOI":"10.1007\/s10207-024-00963-4","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T00:00:00Z","timestamp":1736294400000}}],"container-title":["International Journal of Information Security"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10207-024-00950-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10207-024-00950-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10207-024-00950-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T00:21:11Z","timestamp":1739319671000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10207-024-00950-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":26,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["950"],"URL":"https:\/\/doi.org\/10.1007\/s10207-024-00950-9","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4109219\/v1","asserted-by":"object"}]},"ISSN":["1615-5262","1615-5270"],"issn-type":[{"value":"1615-5262","type":"print"},{"value":"1615-5270","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2025","order":2,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":3,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":4,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s10207-024-00963-4","URL":"https:\/\/doi.org\/10.1007\/s10207-024-00963-4","order":5,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"36"}}