{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:23:32Z","timestamp":1781018612150,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T00:00:00Z","timestamp":1774224000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,23]]},"DOI":"10.1145\/3748522.3779846","type":"proceedings-article","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T14:17:49Z","timestamp":1781014669000},"page":"1038-1047","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Battling Phish: An Empirical Comparison of ML, DL, and LLM in Phishing URL Detection Across Datasets"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2126-6251","authenticated-orcid":false,"given":"Arifa Islam","family":"Champa","sequence":"first","affiliation":[{"name":"Computer Science, Idaho State University, Pocatello, ID, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3815-8925","authenticated-orcid":false,"given":"Md Fazle","family":"Rabbi","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Bangladesh Army International University of Science and Technology, Cumilla, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5353-5030","authenticated-orcid":false,"given":"Minhaz","family":"Zibran","sequence":"additional","affiliation":[{"name":"Computer Science, Idaho State University, Pocatello, ID, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3109091"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3168235"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18576\/jsap\/130108"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/WorldS450073.2020.9210363"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","unstructured":"Anonymous Author. 2025. Replication Package of \"Battling Phish\". 10.6084\/m9.figshare.30324559.v1","DOI":"10.6084\/m9.figshare.30324559.v1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.08.055"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jisa.2023.103553"},{"key":"e_1_3_2_1_8_1","volume-title":"Towards lightweight url-based phishing detection. Future internet 13, 6","author":"Butnaru Andrei","year":"2021","unstructured":"Andrei Butnaru, Alexios Mylonas, and Nikolaos Pitropakis. 2021. Towards lightweight url-based phishing detection. Future internet 13, 6 (2021), 154."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622407.1622416"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_11_1","volume-title":"The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC genomics 21, 1","author":"Chicco Davide","year":"2020","unstructured":"Davide Chicco and Giuseppe Jurman. 2020. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC genomics 21, 1 (2020), 6."},{"key":"e_1_3_2_1_12_1","first-page":"108","article-title":"A machine learning approach for phishing attack detection","volume":"3","author":"Choudhary T.","year":"2023","unstructured":"T. Choudhary, S. Mhapankar, R. Bhddha, A. Kharuk, and R. Patil. 2023. A machine learning approach for phishing attack detection. Journal of artificial intelligence and technology 3, 3 (2023), 108\u2013113.","journal-title":"Journal of artificial intelligence and technology"},{"key":"e_1_3_2_1_13_1","volume-title":"Int. Conf. on Theoretical and Applied Computing. Springer, 171\u2013184","author":"\u00c7olhak Furkan","year":"2024","unstructured":"Furkan \u00c7olhak, Mert \u0130lhan Ecevit, Bilal Emir U\u00e7ar, Reiner Creutzburg, and Hasan Da\u011f. 2024. Phishing website detection through multi-model analysis of html content. In Int. Conf. on Theoretical and Applied Computing. Springer, 171\u2013184."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2957750"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1. 4171\u20134186."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2023.103378"},{"key":"e_1_3_2_1_17_1","volume-title":"Multimedia Security: Algorithm Development, Analysis and Applications","author":"Gandotra E.","year":"2021","unstructured":"E. Gandotra and D. Gupta. 2021. An efficient approach for phishing detection using machine learning. Multimedia Security: Algorithm Development, Analysis and Applications (2021), 239\u2013253."},{"key":"e_1_3_2_1_18_1","first-page":"1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin Y.","year":"2016","unstructured":"Y. Ganin, E. Ustinova, H. Ajakan, P. Germain, H. Larochelle, F. Laviolette, M. March, and V. Lempitsky. 2016. Domain-adversarial training of neural networks. Journal of machine learning research 17, 59 (2016), 1\u201335.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_19_1","volume-title":"Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow. \" O'Reilly Media","author":"G\u00e9ron Aur\u00e9lien","unstructured":"Aur\u00e9lien G\u00e9ron. 2022. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow. \" O'Reilly Media, Inc.\"."},{"key":"e_1_3_2_1_20_1","volume-title":"https:\/\/github.com\/simplerhacking\/Phishing-Keyword-List. (Verified","author":"Keywords Phishing","year":"2025","unstructured":"GitHub. 2023. Phishing Keywords. https:\/\/github.com\/simplerhacking\/Phishing-Keyword-List. (Verified: Dec 2025)."},{"key":"e_1_3_2_1_21_1","volume-title":"Revisiting deep learning models for tabular data. Advances in neural information processing systems 34","author":"Gorishniy Yury","year":"2021","unstructured":"Yury Gorishniy, Ivan Rubachev, Valentin Khrulkov, and Artem Babenko. 2021. Revisiting deep learning models for tabular data. Advances in neural information processing systems 34 (2021), 18932\u201318943."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2021.04.023"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40745-022-00379-8"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104347"},{"key":"e_1_3_2_1_25_1","first-page":"2021","article-title":"Web page phishing detection","volume":"3","author":"Hannousse A.","year":"2021","unstructured":"A. Hannousse and S. Yahiouche. 2021. Web page phishing detection. Mendeley Data 3 (2021), 2021.","journal-title":"Mendeley Data"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02985802"},{"key":"e_1_3_2_1_27_1","volume-title":"Tabtrans-former: Tabular data modeling using contextual embeddings. arXiv preprint arXiv:2012.06678","author":"Huang Xin","year":"2020","unstructured":"Xin Huang, Ashish Khetan, Milan Cvitkovic, and Zohar Karnin. 2020. Tabtrans-former: Tabular data modeling using contextual embeddings. arXiv preprint arXiv:2012.06678 (2020)."},{"key":"e_1_3_2_1_28_1","volume-title":"bert-finetuned-phishing. https:\/\/huggingface.co\/ealvaradob\/bert-finetuned-phishing. (Verified","author":"Face Hugging","year":"2025","unstructured":"Hugging Face. 2024. bert-finetuned-phishing. https:\/\/huggingface.co\/ealvaradob\/bert-finetuned-phishing. (Verified: May 2025)."},{"key":"e_1_3_2_1_29_1","volume-title":"urlbert-tiny-v4-phishing-classifier. https:\/\/huggingface.co\/CrabInHoney\/urlbert-tiny-v4-phishing-classifier. (Verified","author":"Face Hugging","year":"2025","unstructured":"Hugging Face. 2025. urlbert-tiny-v4-phishing-classifier. https:\/\/huggingface.co\/CrabInHoney\/urlbert-tiny-v4-phishing-classifier. (Verified: May 2025)."},{"key":"e_1_3_2_1_30_1","first-page":"1104","article-title":"Advanced Threat Detection Using Soft and Hard Voting Techniques in Ensemble Learning","volume":"5","author":"Jabbar Hanan","year":"2024","unstructured":"Hanan Jabbar. 2024. Advanced Threat Detection Using Soft and Hard Voting Techniques in Ensemble Learning. J. Robot. Control 5, 4 (2024), 1104\u20131116.","journal-title":"J. Robot. Control"},{"key":"e_1_3_2_1_31_1","unstructured":"G. Klambauer T. Unterthiner A. Mayr and S. Hochreiter. 2017. Self-normalizing neural networks. Adv. Neural Inf. Process. Syst. 30 (2017)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1201\/9781315108230"},{"key":"e_1_3_2_1_33_1","volume-title":"KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection. arXiv preprint arXiv:2403","author":"Li Y.","year":"2024","unstructured":"Y. Li, C. Huang, S. Deng, M. Lock, T. Cao, N. Oo, B. Hooi, and H. Lim. 2024. KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection. arXiv preprint arXiv:2403.02253 (2024)."},{"key":"e_1_3_2_1_34_1","volume-title":"Continuous multi-task pre-training for malicious URL detection and webpage classification. Computer Networks","author":"Li Yujie","year":"2025","unstructured":"Yujie Li, Yiwei Liu, Peiyue Li, Yifan Jia, and Yanbin Wang. 2025. Continuous multi-task pre-training for malicious URL detection and webpage classification. Computer Networks (2025), 111513."},{"key":"e_1_3_2_1_35_1","first-page":"3021","article-title":"Real-time phishing detection using deep learning methods by extensions","volume":"14","author":"Linh Dam Minh","year":"2024","unstructured":"Dam Minh Linh, Ha Duy Hung, Han Minh Chau, Quang Sy Vu, and Thanh-Nam Tran. 2024. Real-time phishing detection using deep learning methods by extensions. Int. J. Electr. Comput. Eng. 14, 3 (2024), 3021\u20133035.","journal-title":"Int. J. Electr. Comput. Eng."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626232.3653283"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM52596.2021.9653028"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2014.2377295"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-022-03604-4"},{"key":"e_1_3_2_1_40_1","article-title":"Comparative study of machine learning algorithms for phishing website detection","volume":"14","author":"Omari Kamal","year":"2023","unstructured":"Kamal Omari. 2023. Comparative study of machine learning algorithms for phishing website detection. Int. J. Adv. Comput. Sci. Appl. 14, 9 (2023).","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2019.12.005"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386782"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"R. Potpelwar U. Kulkarni and J. Waghmare. 2025. LegitPhish: A Large-Scale Annotated Dataset for URL-Based Phishing Detection. Data in Brief (2025).","DOI":"10.1016\/j.dib.2025.111972"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2023.103545"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92178-0_8"},{"key":"e_1_3_2_1_46_1","volume-title":"Detecting Phishing Emails Using ML and NLP. In International Conference on Software Engineering Research, Management and Applications. IEEE, 77\u201383","author":"Rabbi Md Fazle","year":"2023","unstructured":"Md Fazle Rabbi, Arifa Champa, and Minhaz Zibran. 2023. Phishy? Detecting Phishing Emails Using ML and NLP. In International Conference on Software Engineering Research, Management and Applications. IEEE, 77\u201383."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.matpr.2021.04.041"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3409049"},{"key":"e_1_3_2_1_49_1","volume-title":"Beyond sharing weights for deep domain adaptation","author":"Rozantsev Artem","year":"2018","unstructured":"Artem Rozantsev, Mathieu Salzmann, and Pascal Fua. 2018. Beyond sharing weights for deep domain adaptation. IEEE transactions on pattern analysis and machine intelligence 41, 4 (2018), 801\u2013814."},{"key":"e_1_3_2_1_50_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2024.1308634"},{"key":"e_1_3_2_1_52_1","first-page":"2018","article-title":"Phishing dataset for machine learning: Feature evaluation","volume":"1","author":"Tan Choon Lin","year":"2018","unstructured":"Choon Lin Tan. 2018. Phishing dataset for machine learning: Feature evaluation. Mendeley Data 1 (2018), 2018.","journal-title":"Mendeley Data"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1002\/spy2.120"},{"key":"e_1_3_2_1_54_1","volume-title":"Phishing Site URLs: Malicious and Phishing attacks URLs. https:\/\/www.kaggle.com\/datasets\/taruntiwarihp\/phishing-site-urls\/data. (Verified","author":"Tiwary T.","year":"2025","unstructured":"T. Tiwary. 2020. Phishing Site URLs: Malicious and Phishing attacks URLs. https:\/\/www.kaggle.com\/datasets\/taruntiwarihp\/phishing-site-urls\/data. (Verified: Apr 2025)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-169429"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2020.106438"},{"key":"e_1_3_2_1_57_1","volume-title":"2021 Verizon Data Breach Investigations Report. (May","author":"Widup Suzanne","year":"2021","unstructured":"Suzanne Widup, Alex Pinto, David Hylender, Gabriel Bassett, and Philippe Langlois. 2021. 2021 Verizon Data Breach Investigations Report. (May 2021)."},{"key":"e_1_3_2_1_58_1","volume-title":"Chin. Conf. Trusted Comput. Inf. Secur. Springer, 372\u2013388","author":"Yan Huaizhi","year":"2018","unstructured":"Huaizhi Yan, Xin Zhang, Jiangwei Xie, and Changzhen Hu. 2018. Detecting malicious urls using a deep learning approach based on stacked denoising autoencoder. In Chin. Conf. Trusted Comput. Inf. Secur. Springer, 372\u2013388."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02117-4"},{"key":"e_1_3_2_1_60_1","volume-title":"Domain generalization: A survey","author":"Zhou Kaiyang","year":"2022","unstructured":"Kaiyang Zhou, Ziwei Liu, Yu Qiao, Tao Xiang, and Chen Change Loy. 2022. Domain generalization: A survey. IEEE transactions on pattern analysis and machine intelligence 45, 4 (2022), 4396\u20134415."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2023.103561"}],"event":{"name":"SAC '26: 41st ACM\/SIGAPP Symposium on Applied Computing","location":"Grand Hotel Palace Thessaloniki Greece","acronym":"SAC '26","sponsor":["SIGAPP ACM Special Interest Group on Applied Computing"]},"container-title":["Proceedings of the 41st ACM\/SIGAPP Symposium on Applied Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3748522.3779846","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T14:33:46Z","timestamp":1781015626000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3748522.3779846"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,23]]},"references-count":61,"alternative-id":["10.1145\/3748522.3779846","10.1145\/3748522"],"URL":"https:\/\/doi.org\/10.1145\/3748522.3779846","relation":{},"subject":[],"published":{"date-parts":[[2026,3,23]]},"assertion":[{"value":"2026-06-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}