{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T04:24:22Z","timestamp":1764995062801,"version":"3.46.0"},"reference-count":25,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2025,12,1]]},"DOI":"10.1587\/transinf.2024ofl0002","type":"journal-article","created":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T22:08:13Z","timestamp":1756159693000},"page":"1457-1460","source":"Crossref","is-referenced-by-count":0,"title":["Domain-Adaptive Pre-Training of Language Models for Text Mining of Cybersecurity Documents"],"prefix":"10.1587","volume":"E108.D","author":[{"given":"Kennosuke","family":"AOTA","sequence":"first","affiliation":[{"name":"The Department of Electrical and Electronic Engineering, Kobe University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Makoto","family":"TAKITA","sequence":"additional","affiliation":[{"name":"The Department of Electrical and Electronic Engineering, Kobe University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thin Tharaphe","family":"THEIN","sequence":"additional","affiliation":[{"name":"The Department of Electrical and Electronic Engineering, Kobe University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroki","family":"KUZUNO","sequence":"additional","affiliation":[{"name":"The Department of Electrical and Electronic Engineering, Kobe University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masami","family":"MOHRI","sequence":"additional","affiliation":[{"name":"The Faculty of Informatics and the Institute of Informatics, Kindai University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshiaki","family":"SHIRAISHI","sequence":"additional","affiliation":[{"name":"The Department of Electrical and Electronic Engineering, Kobe University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] \u201cNATIONAL VULNERABILTY DATABASE (NVD).\u201d NIST, https:\/\/nvd.nist.gov, Accessed 6 Dec. 2024."},{"key":"2","unstructured":"[2] \u201cCommon Vulnerabilities and Exposures (CVE).\u201d CVE, https:\/\/cve.mitre.org, Accessed 6 Dec. 2024."},{"key":"3","unstructured":"[3] Y. Goldberg and O. Levy, \u201cWord2vec Explained: Deriving Mikolov et al.\u2019s Negative-Sampling Word-Embedding Method,\u201d arXiv:1402.3722, 15 Feb. 2014."},{"key":"4","unstructured":"[4] J. Devlin et al., \u201cBERT: Pre-Training of Deep Bidirectional Transformers for Language,\u201d arXiv:1810.04805, 24 May 2019."},{"key":"5","unstructured":"[5] E. Aghaei, X. Niu, W. Shadid, and E. Al-Shaer, \u201cSecureBERT: A Domain-Specific Language Model for Cybersecurity,\u201d *arXiv preprint arXiv:2204.02685*, 2022. [Online]. Available: https:\/\/arxiv.org\/abs\/2204.02685"},{"key":"6","unstructured":"[6] Y. Liu et al., \u201cRoBERTa: A Robustly Optimized BERT Pretraining Approach,\u201d arXiv:1907.11692, 26 July 2019."},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] S.K. Lim, A.O. Muis, W. Lu, and C.H. Ong, \u201cMalwareTextDB: A Database for Annotated Malware Articles,\u201d Proc. 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Vancouver, Canada, pp.1557-1567, July 2017, doi: 10.18653\/v1\/P17-1143. [Online]. Available: https:\/\/aclanthology.org\/P17-1143\/","DOI":"10.18653\/v1\/P17-1143"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] P. Evangelatos, C. Iliou, T. Mavropoulos, K. Apostolou, T. Tsikrika, S. Vrochidis, and I. Kompatsiaris, \u201cNamed Entity Recognition in Cyber Threat Intelligence Using Transformer-based Models,\u201d 2021 IEEE Int. Conf. Cyber Security and Resilience (CSR), pp.348-353, 2021. doi: 10.1109\/CSR51186.2021.9527981. 10.1109\/csr51186.2021.9527981","DOI":"10.1109\/CSR51186.2021.9527981"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] X. Wang, X. Liu, S. Ao, N. Li, Z. Jiang, Z. Xu, Z. Xiong, M. Xiong, and X. Zhang, \u201cDNRTI: A Large-Scale Dataset for Named Entity Recognition in Threat Intelligence,\u201d 2020 IEEE 19th Int. Conf. Trust, Security and Privacy in Computing and Communications (TrustCom), Guangzhou, China, pp.1842-1848, 2020. doi: 10.1109\/TrustCom50675.2020.00252. 10.1109\/trustcom50675.2020.00252","DOI":"10.1109\/TrustCom50675.2020.00252"},{"key":"10","unstructured":"[10] \u201cThe Barracuda Blog.\u201d Barracuda Networks, Inc., https:\/\/blog.barracuda.com, Accessed 6 Dec. 2024."},{"key":"11","unstructured":"[11] \u201cCheck Point Software - Blog.\u201d Check Point Software Technologies Ltd., https:\/\/blog.checkpoint.com, Accessed 6 Dec. 2024."},{"key":"12","unstructured":"[12] \u201c360 Netlab Blog - Network Security Research Lab at 360,\u201d 360Netlab, https:\/\/blog.netlab.360.com, Accessed 6 Dec. 2024."},{"key":"13","unstructured":"[13] \u201cCisco Talos Blog,\u201d Cisco Systems, Inc., https:\/\/blog.talosintelligence.com, Accessed 6 Dec. 2024."},{"key":"14","unstructured":"[14] \u201cTrend Micro Blog,\u201d Trend Micro Incorporated, https:\/\/blog.trendmicro.com, Accessed 6 Dec. 2024."},{"key":"15","unstructured":"[15] \u201cSymantec Enterprise Blogs,\u201d Broadcom Inc., https:\/\/symantec-enterprise-blogs.security.com, Accessed 6 Dec. 2024."},{"key":"16","unstructured":"[16] \u201cUnit 42 - Latest Cyber Security Research \u2014 Palo Alto Networks,\u201d Palo Alto Networks, Inc., https:\/\/unit42.paloaltonetworks.com, Accessed 6 Dec. 2024."},{"key":"17","unstructured":"[17] \u201cCybersecurity Blog \u2014 CrowdStrike,\u201d CrowdStrike, Inc., https:\/\/www.crowdstrike.com, Accessed 6 Dec. 2024."},{"key":"18","unstructured":"[18] \u201cBlog \u2014 Darktrace,\u201d Darktrace Holdings Limited, https:\/\/darktrace.com, Accessed 6 Dec. 2024."},{"key":"19","unstructured":"[19] \u201cDruva Blog - Data Protection for the Cloud Era \u2014 Druva,\u201d Druva Inc., https:\/\/www.druva.com, Accessed 6 Dec. 2024."},{"key":"20","unstructured":"[20] \u201cFireEye Blog - Threat Research and Analysis \u2014 FireEye,\u201d FireEye, Inc., https:\/\/www.fireeye.com, Accessed 6 Dec. 2024."},{"key":"21","unstructured":"[21] \u201cFortinet Blog - Broad, Integrated, Automated Cybersecurity,\u201d Fortinet, Inc., https:\/\/www.fortinet.com, Accessed 6 Dec. 2024."},{"key":"22","unstructured":"[22] \u201cNETSCOUT Blog \u2014 NETSCOUT,\u201d NETSCOUT Systems, Inc., https:\/\/www.netscout.com, Accessed 6 Dec. 2024."},{"key":"23","unstructured":"[23] \u201cSecPod Blog - Latest News and Security Intelligence - SecPod Blog,\u201d SecPod Technologies Pvt. Ltd., https:\/\/www.secpod.com, Accessed 6 Dec. 2024."},{"key":"24","unstructured":"[24] \u201cSecureworks: Cybersecurity Leader, Proven Threat Defense \u2014 Secureworks,\u201d Secureworks, Inc., https:\/\/www.secureworks.com, Accessed 6 Dec. 2024."},{"key":"25","unstructured":"[25] \u201cWeLiveSecurity,\u201d ESET, spol. s r.o., https:\/\/www.welivesecurity.com, Accessed 6 Dec. 2024."}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E108.D\/12\/E108.D_2024OFL0002\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T03:27:45Z","timestamp":1764991665000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E108.D\/12\/E108.D_2024OFL0002\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":25,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2024ofl0002","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"type":"print","value":"0916-8532"},{"type":"electronic","value":"1745-1361"}],"subject":[],"published":{"date-parts":[[2025,12,1]]},"article-number":"2024OFL0002"}}