{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:47:11Z","timestamp":1780512431521,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T00:00:00Z","timestamp":1693267200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,29]]},"DOI":"10.1145\/3600160.3600163","type":"proceedings-article","created":{"date-parts":[[2023,8,9]],"date-time":"2023-08-09T22:54:41Z","timestamp":1691621681000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Canary in Twitter Mine: Collecting Phishing Reports from Experts and Non-experts"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4470-2139","authenticated-orcid":false,"given":"Hiroki","family":"Nakano","sequence":"first","affiliation":[{"name":"NTT Security (Japan) KK, Japan and Yokohama National University, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7532-6633","authenticated-orcid":false,"given":"Daiki","family":"Chiba","sequence":"additional","affiliation":[{"name":"NTT Security (Japan) KK, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1942-0335","authenticated-orcid":false,"given":"Takashi","family":"Koide","sequence":"additional","affiliation":[{"name":"NTT Security (Japan) KK, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8103-8244","authenticated-orcid":false,"given":"Naoki","family":"Fukushi","sequence":"additional","affiliation":[{"name":"NTT Security (Japan) KK, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6414-8815","authenticated-orcid":false,"given":"Takeshi","family":"Yagi","sequence":"additional","affiliation":[{"name":"NTT, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4415-5310","authenticated-orcid":false,"given":"Takeo","family":"Hariu","sequence":"additional","affiliation":[{"name":"NTT Security (Japan) KK, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0964-8631","authenticated-orcid":false,"given":"Katsunari","family":"Yoshioka","sequence":"additional","affiliation":[{"name":"Yokohama National University, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7965-4888","authenticated-orcid":false,"given":"Tsutomu","family":"Matsumoto","sequence":"additional","affiliation":[{"name":"Yokohama National University, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,8,29]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Ashutosh Adhikari Achyudh Ram Raphael Tang and Jimmy Lin. 2019. DocBERT: BERT for Document Classification. http:\/\/arxiv.org\/abs\/1904.08398"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/eCrime.2012.6489521"},{"key":"e_1_3_2_1_3_1","first-page":"18","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics (COLING). 1638\u20131649","author":"Akbik Alan","year":"2018","unstructured":"Alan Akbik, Duncan Blythe, and Roland Vollgraf. 2018. Contextual String Embeddings for Sequence Labeling. In Proceedings of the 27th International Conference on Computational Linguistics (COLING). 1638\u20131649. https:\/\/aclanthology.org\/C18-1139"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3051085"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58951-6_11"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Tim Berners-Lee Roy\u00a0T. Fielding and Larry\u00a0M Masinter. 2005. Uniform Resource Identifier (URI): Generic Syntax. RFC 3986. https:\/\/www.rfc-editor.org\/info\/rfc3986.","DOI":"10.17487\/rfc3986"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 30th USENIX Security Symposium (USENIX Security). USENIX Association, 3757\u20133774","author":"Bijmans Hugo","year":"2021","unstructured":"Hugo Bijmans, Tim Booij, Anneke Schwedersky, Aria Nedgabat, and Rolf van Wegberg. 2021. Catching Phishers By Their Bait: Investigating the Dutch Phishing Landscape through Phishing Kit Detection. In Proceedings of the 30th USENIX Security Symposium (USENIX Security). USENIX Association, 3757\u20133774. https:\/\/www.usenix.org\/conference\/usenixsecurity21\/presentation\/bijmans"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052654"},{"key":"e_1_3_2_1_9_1","unstructured":"Twitter Dev. 2023. Twitter is enforcing its long-standing API rules. https:\/\/twitter.com\/TwitterDev\/status\/1615405842735714304."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_11_1","unstructured":"dynamic.domains. 2022. 25 Dynamic DNS (DDNS) providers - dynamic.domains. https:\/\/dynamic.domains\/dynamic-dns\/providers-list\/default.aspx."},{"key":"e_1_3_2_1_12_1","unstructured":"Farsight Security Inc. 2020. DNSDB. https:\/\/www.dnsdb.info\/."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.62"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 19th Network and Distributed System Security Symposium (NDSS). The Internet Society. http:\/\/cucis.ece.northwestern.edu\/publications\/pdf\/GaoChe12","author":"Gao Hongyu","year":"2012","unstructured":"Hongyu Gao, Yan Chen, Kathy Lee, Diana Palsetia, and Alok\u00a0N. Choudhary. 2012. Towards Online Spam Filtering in Social Networks. In Proceedings of the 19th Network and Distributed System Security Symposium (NDSS). The Internet Society. http:\/\/cucis.ece.northwestern.edu\/publications\/pdf\/GaoChe12.pdf"},{"key":"e_1_3_2_1_15_1","unstructured":"Google. 2022. Google Safe Browsing. https:\/\/safebrowsing.google.com\/."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186119"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01937276"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 28th USENIX Security Symposium (USENIX Security). USENIX Association, 1273\u20131290","author":"Ho Grant","year":"2019","unstructured":"Grant Ho, Asaf Cidon, Lior Gavish, Marco Schweighauser, Vern Paxson, Stefan Savage, Geoffrey\u00a0M. Voelker, and David Wagner. 2019. Detecting and Characterizing Lateral Phishing at Scale. In Proceedings of the 28th USENIX Security Symposium (USENIX Security). USENIX Association, 1273\u20131290. https:\/\/www.usenix.org\/conference\/usenixsecurity19\/presentation\/ho"},{"key":"e_1_3_2_1_19_1","unstructured":"Twitter\u00a0IOC Hunter. 2022. Twitter IOC Hunter. http:\/\/tweettioc.com\/."},{"key":"e_1_3_2_1_20_1","unstructured":"Proofpoint Inc.2021. Smishing reports increase nearly 700% in first six months of this year. https:\/\/news.sky.com\/story\/smishing-reports-increase-nearly-700-in-first-six-months-of-this-year-12407504."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"Glenn Jocher 2020. ultralytics\/yolov5: v3.1 - Bug Fixes and Performance Improvements. https:\/\/doi.org\/10.5281\/zenodo.4154370","DOI":"10.5281\/zenodo.4154370"},{"key":"e_1_3_2_1_22_1","unstructured":"Eoghan Keany. 2020. BorutaShap : A wrapper feature selection method which combines the Boruta feature selection algorithm with Shapley values.https:\/\/zenodo.org\/badge\/latestdoi\/255354538"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132866"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3433210.3453100"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3320269.3384714"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v036.i11"},{"key":"e_1_3_2_1_27_1","unstructured":"Megagon Labs. 2021. megagonlabs\/transformers-ud-japanese-electra-base-ginza \u00b7 Hugging Face. https:\/\/huggingface.co\/megagonlabs\/transformers-ud-japanese-electra-base-ginza."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23386"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 19th Network and Distributed System Security Symposium (NDSS). The Internet Society. https:\/\/www.ndss-symposium.org\/wp-content\/uploads\/2017\/09\/11_1.pdf","author":"Lee Sangho","year":"2012","unstructured":"Sangho Lee and Jong Kim. 2012. Warningbird: Detecting suspicious URLs in twitter stream. In Proceedings of the 19th Network and Distributed System Security Symposium (NDSS). The Internet Society. https:\/\/www.ndss-symposium.org\/wp-content\/uploads\/2017\/09\/11_1.pdf"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 30th USENIX Security Symposium (USENIX Security). USENIX Association, 3793\u20133810","author":"Lin Yun","year":"2021","unstructured":"Yun Lin, Ruofan Liu, Dinil\u00a0Mon Divakaran, Jun\u00a0Yang Ng, Qing\u00a0Zhou Chan, Yiwen Lu, Yuxuan Si, Fan Zhang, and Jin\u00a0Song Dong. 2021. Phishpedia: A Hybrid Deep Learning Based Approach to Visually Identify Phishing Webpages. In Proceedings of the 30th USENIX Security Symposium (USENIX Security). USENIX Association, 3793\u20133810. https:\/\/www.usenix.org\/conference\/usenixsecurity21\/presentation\/lin"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485832.3488012"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106691"},{"key":"e_1_3_2_1_33_1","unstructured":"Microsoft. 2022. Microsoft Defender SmartScreen. https:\/\/docs.microsoft.com\/en-us\/windows\/security\/threat-protection\/microsoft-defender-smartscreen\/microsoft-defender-smartscreen-overview."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"P. Mockapetris. 1987. Domain names - implementation and specification. RFC 1035. https:\/\/www.rfc-editor.org\/info\/rfc1035.","DOI":"10.17487\/rfc1035"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC51774.2021.00102"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 24th USENIX Security Symposium (USENIX Security). USENIX Association, 1025\u20131040","author":"Nelms Terry","year":"2015","unstructured":"Terry Nelms, Roberto Perdisci, Manos Antonakakis, and Mustaque Ahamad. 2015. WebWitness: Investigating, Categorizing, and Mitigating Malware Download Paths. In Proceedings of the 24th USENIX Security Symposium (USENIX Security). USENIX Association, 1025\u20131040. https:\/\/www.usenix.org\/conference\/usenixsecurity15\/technical-sessions\/presentation\/nelms"},{"key":"e_1_3_2_1_37_1","unstructured":"NIST. 2021. National Vulnerability Database. https:\/\/nvd.nist.gov\/."},{"key":"e_1_3_2_1_38_1","unstructured":"Rodrigo Nogueira and Kyunghyun Cho. 2019. Passage Re-ranking with BERT. http:\/\/arxiv.org\/abs\/1901.04085"},{"key":"e_1_3_2_1_39_1","unstructured":"Tesseract OCR. 2022. Tesseract OCR. https:\/\/github.com\/tesseract-ocr\/tesseract."},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the 29th USENIX Security Symposium (USENIX Security). USENIX Association, 361\u2013377","author":"Oest Adam","year":"2020","unstructured":"Adam Oest, Penghui Zhang, Brad Wardman, Eric Nunes, Jakub Burgis, Ali Zand, Kurt Thomas, Adam Doup\u00e9, and Gail-Joon Ahn. 2020. Sunrise to Sunset: Analyzing the End-to-end Life Cycle and Effectiveness of Phishing Attacks at Scale. In Proceedings of the 29th USENIX Security Symposium (USENIX Security). USENIX Association, 361\u2013377. https:\/\/www.usenix.org\/conference\/usenixsecurity20\/presentation\/oest-sunrise"},{"key":"e_1_3_2_1_41_1","unstructured":"OpenPhish. 2022. OpenPhish. https:\/\/openphish.com."},{"key":"e_1_3_2_1_42_1","unstructured":"opmusic. 2023. SpamHunter_dataset. https:\/\/github.com\/opmusic\/SpamHunter_dataset\/blob\/main\/sms_spam_urls\/tweet_sms_url_latest.txt."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355369.3355585"},{"key":"e_1_3_2_1_44_1","unstructured":"PeterDaveHello. 2022. URL Shorteners. https:\/\/github.com\/PeterDaveHello\/url-shorteners."},{"key":"e_1_3_2_1_45_1","unstructured":"PhishTank. 2022. PhishTank. https:\/\/www.phishtank.com\/."},{"key":"e_1_3_2_1_46_1","unstructured":"The\u00a0Spamhaus Project. 2022. The Top 10 Most Abused TLDs. https:\/\/www.spamhaus.org\/statistics\/tlds\/."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.28"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/eCrime54498.2021.9738786"},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of the 24th USENIX Security Symposium (USENIX Security). USENIX Association, 1041\u20131056","author":"Sabottke Carl","year":"2015","unstructured":"Carl Sabottke, Octavian Suciu, and Tudor Dumitras. 2015. Vulnerability Disclosure in the Age of Social Media: Exploiting Twitter for Predicting Real-World Exploits. In Proceedings of the 24th USENIX Security Symposium (USENIX Security). USENIX Association, 1041\u20131056. https:\/\/www.usenix.org\/conference\/usenixsecurity15\/technical-sessions\/presentation\/sabottke"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3217795"},{"key":"e_1_3_2_1_51_1","unstructured":"SafetyDetectives. 2023. 11 Facts + Stats on Smishing (SMS Phishing) in 2023. https:\/\/www.safetydetectives.com\/blog\/what-is-smishing-sms-phishing-facts\/."},{"key":"e_1_3_2_1_52_1","unstructured":"SecurityTrails. 2022. urlscan.io. https:\/\/urlscan.io\/."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449797"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3320269.3384721"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-45744-4_1"},{"key":"e_1_3_2_1_56_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML). PMLR, 6105\u20136114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In Proceedings of the 36th International Conference on Machine Learning (ICML). PMLR, 6105\u20136114. http:\/\/arxiv.org\/abs\/1905.11946"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3559351"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2068816.2068840"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134067"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3278532.3278569"},{"key":"e_1_3_2_1_61_1","unstructured":"Cisco Umbrella. 2023. On the trail of malicious dynamic DNS domains - Cisco Umbrella. https:\/\/umbrella.cisco.com\/blog\/on-the-trail-of-malicious-dynamic-dns-domains."},{"key":"e_1_3_2_1_62_1","unstructured":"VirusTotal. 2022. VirusTotal. https:\/\/www.virustotal.com\/."},{"key":"e_1_3_2_1_63_1","unstructured":"WeLiveSecurity. 2021. Why do we fall for SMS phishing scams so easily? | WeLiveSecurity. https:\/\/www.welivesecurity.com\/2021\/01\/22\/why-do-we-fall-sms-phishing-scams-so-easily\/."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/2019599.2019606"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/2187836.2187847"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00021"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2018.00039"}],"event":{"name":"ARES 2023: The 18th International Conference on Availability, Reliability and Security","location":"Benevento Italy","acronym":"ARES 2023"},"container-title":["Proceedings of the 18th International Conference on Availability, Reliability and Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3600160.3600163","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3600160.3600163","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:13Z","timestamp":1750178173000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3600160.3600163"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,29]]},"references-count":67,"alternative-id":["10.1145\/3600160.3600163","10.1145\/3600160"],"URL":"https:\/\/doi.org\/10.1145\/3600160.3600163","relation":{},"subject":[],"published":{"date-parts":[[2023,8,29]]},"assertion":[{"value":"2023-08-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}