{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T11:05:20Z","timestamp":1784027120122,"version":"3.55.0"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032207319","type":"print"},{"value":"9783032207326","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-20732-6_1","type":"book-chapter","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T10:28:53Z","timestamp":1784024933000},"page":"3-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving the\u00a0Accuracy of\u00a0Embeddings for\u00a0Matching Tasks in\u00a0Cybersecurity Using Generated Dictionaries"],"prefix":"10.1007","author":[{"given":"Arian","family":"Soltani","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abir","family":"Bala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Djeff Kanda","family":"Nkashama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pierre-Martin","family":"Tardif","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ayoub","family":"Bahnasse","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Frappier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Froduald","family":"Kabanza","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Abdeen, B., Al-Shaer, E., Singhal, A., Khan, L., Hamlen, K.: SMET: semantic mapping of CVE to ATT&CK and its application to cybersecurity. In: IFIP Annual Conference on Data and Applications Security and Privacy, pp. 243\u2013260. Springer (2023)","DOI":"10.1007\/978-3-031-37586-6_15"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Abdeen, B., Al-Shaer, E., Singhal, A., Khan, L., Hamlen, K.W.: Smet: semantic mapping of cti reports and CVE to att&ck for advanced threat intelligence. J. Comput. Secur. (Preprint), 1\u201320 (2024)","DOI":"10.3233\/JCS-230218"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Aghaei, E., Niu, X., Shadid, W., Al-Shaer, E.: SecureBERT: a domain-specific language model for cybersecurity. In: International Conference on Security and Privacy in Communication Systems, pp. 39\u201356. Springer (2022)","DOI":"10.1007\/978-3-031-25538-0_3"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Alam, M.T., Bhusal, D., Park, Y., Rastogi, N.: Looking beyond iocs: automatically extracting attack patterns from external CTI. In: Proceedings of the 26th International Symposium on Research in Attacks, Intrusions and Defenses, pp. 92\u2013108 (2023)","DOI":"10.1145\/3607199.3607208"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Beltagy, I., Lo, K., Cohan, A.: SciBERT: a pretrained language model for scientific text. arXiv preprint arXiv:1903.10676 (2019)","DOI":"10.18653\/v1\/D19-1371"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Bose, A., Yang, H., Shivers, M., Orazgeldiyev, A., Hsu, W.H.: Context-augmented key phrase extraction from short texts for cyber threat intelligence tasks. In: 2023 IEEE International Conference on Intelligence and Security Informatics (ISI), pp.\u00a01\u20136. IEEE (2023)","DOI":"10.1109\/ISI58743.2023.10297274"},{"key":"1_CR7","unstructured":"Bubeck, S., et\u00a0al.: Sparks of artificial general intelligence: early experiments with GPT-4. arXiv preprint arXiv:2303.12712 (2023)"},{"key":"1_CR8","unstructured":"Cer, D., et\u00a0al.: Universal sentence encoder. arXiv preprint arXiv:1803.11175 (2018)"},{"key":"1_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"EL\u00a0Jaouhari, S., Tamani, N., Jacob, R.I.: Improving ML-based solutions for linking of CVE to MITRE ATT &CK techniques. In: 2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC), pp. 2442\u20132447. IEEE (2024)","DOI":"10.1109\/COMPSAC61105.2024.00392"},{"issue":"9","key":"1_CR11","doi-asserted-by":"publisher","first-page":"314","DOI":"10.3390\/a15090314","volume":"15","author":"O Grigorescu","year":"2022","unstructured":"Grigorescu, O., Nica, A., Dascalu, M., Rughinis, R.: CVE2ATT&CK: BERT-based mapping of CVEs to MITRE ATT&CK techniques. Algorithms 15(9), 314 (2022)","journal-title":"Algorithms"},{"key":"1_CR12","unstructured":"Huang, J., Parthasarathi, P., Rezagholizadeh, M., Chandar, S.: Towards practical tool usage for continually learning LLMs. arXiv preprint arXiv:2404.09339 (2024)"},{"key":"1_CR13","unstructured":"Huggingface: MTEB Leaderboard. https:\/\/huggingface.co\/spaces\/mteb\/leaderboard (2023) [. Accessed 1 Dec 2023]"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Joshi, A., Lal, R., Finin, T., Joshi, A.: Extracting cybersecurity related linked data from text. In: 2013 IEEE Seventh International Conference on Semantic Computing, pp. 252\u2013259. IEEE (2013)","DOI":"10.1109\/ICSC.2013.50"},{"issue":"8","key":"1_CR15","doi-asserted-by":"publisher","first-page":"298","DOI":"10.3390\/info12080298","volume":"12","author":"K Kanakogi","year":"2021","unstructured":"Kanakogi, K., et al.: Tracing CVE vulnerability information to CAPEC attack patterns using natural language processing techniques. Information 12(8), 298 (2021)","journal-title":"Information"},{"key":"1_CR16","doi-asserted-by":"publisher","first-page":"1167","DOI":"10.1016\/j.procs.2024.04.111","volume":"235","author":"K Kota","year":"2024","unstructured":"Kota, K., Manjunatha, A., et al.: CWE prediction using CVE description-the semantic similarity approach. Proc. Comput. Sci. 235, 1167\u20131178 (2024)","journal-title":"Proc. Comput. Sci."},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Kuppa, A., Aouad, L., Le-Khac, N.A.: Linking CVE\u2019s to MITRE ATT&CK Techniques. In: Proceedings of the 16th International Conference on Availability, Reliability and Security, pp. 1\u201312 (2021)","DOI":"10.1145\/3465481.3465758"},{"key":"1_CR18","unstructured":"Li, X., Li, J.: Angle-optimized text embeddings. arXiv preprint arXiv:2309.12871 (2023)"},{"key":"1_CR19","unstructured":"Li, Z., Zhang, X., Zhang, Y., Long, D., Xie, P., Zhang, M.: Towards general text embeddings with multi-stage contrastive learning. arXiv preprint arXiv:2308.03281 (2023)"},{"key":"1_CR20","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"1_CR21","unstructured":"Mendsaikhan, O., Hasegawa, H., Yamaguchi, Y., Shimada, H.: Automatic mapping of vulnerability information to adversary techniques. In: The Fourteenth International Conference on Emerging Security Information, Systems and Technologies SECUREWARE2020 (2020)"},{"key":"1_CR22","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)"},{"key":"1_CR23","unstructured":"MITRE Corporation: MITRE ATT&CK database. https:\/\/attack.mitre.org\/ (2023). [Accessed 19 July 2023]"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Muennighoff, N., Tazi, N., Magne, L., Reimers, N.: MTEB: massive text embedding benchmark. arXiv preprint arXiv:2210.07316 (2022)","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Mumtaz, S., Rodriguez, C., Benatallah, B., Al-Banna, M., Zamanirad, S.: Learning word representation for the cyber security vulnerability domain. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20138. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9207140"},{"key":"1_CR26","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), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Purba, M.D., Chu, B., Al-Shaer, E.: From word embedding to cyber-phrase embedding: comparison of processing cybersecurity texts. In: 2020 IEEE International Conference on Intelligence and Security Informatics (ISI), pp.\u00a01\u20136. IEEE (2020)","DOI":"10.1109\/ISI49825.2020.9280541"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Ranade, P., Piplai, A., Joshi, A., Finin, T.: CyBERT: contextualized embeddings for the cybersecurity domain. In: 2021 IEEE International Conference on Big Data (Big Data), pp. 3334\u20133342. IEEE (2021)","DOI":"10.1109\/BigData52589.2021.9671824"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using siamese BERT-networks. arXiv preprint arXiv:1908.10084 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"1_CR30","unstructured":"Roy, S., Panaousis, E., Noakes, C., Laszka, A., Panda, S., Loukas, G.: SoK: the MITRE ATT&CK framework in research and practice. arXiv preprint arXiv:2304.07411 (2023)"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Soltani, A., Nkashama, D.K., Masakuna, J.F., Frappier, M., Tardif, P.M., Kabanza, F.: Assessing language models for semantic textual similarity in cybersecurity. In: International Conference on Detection of Intrusions and Malware, and Vulnerability Assessment, pp. 370\u2013380. Springer (2024)","DOI":"10.1007\/978-3-031-64171-8_19"},{"key":"1_CR32","first-page":"16857","volume":"33","author":"K Song","year":"2020","unstructured":"Song, K., Tan, X., Qin, T., Lu, J., Liu, T.Y.: MPNet: masked and permuted pre-training for language understanding. Adv. Neural. Inf. Process. Syst. 33, 16857\u201316867 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR33","unstructured":"The Center for Threat-Informed Defense: Mapping MITRE ATT&CK\u00aeto CVEs for Impact. https:\/\/ctid.mitre.org\/projects\/mapping-attck-to-cve-for-impact\/ (2021). Accessed 19 Sept 2024"},{"key":"1_CR34","unstructured":"The Center for Threat-Informed Defense: Threat Report ATT&CK Mapper (TRAM). https:\/\/ctid.mitre.org\/projects\/threat-report-attck-mapper-tram (2023). Accessed 19 Sept 2024"},{"key":"1_CR35","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"1_CR36","unstructured":"Wang, L., et al.: Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533 (2022)"},{"key":"1_CR37","first-page":"5776","volume":"33","author":"W Wang","year":"2020","unstructured":"Wang, W., Wei, F., Dong, L., Bao, H., Yang, N., Zhou, M.: MiniLM: deep self-attention distillation for task-agnostic compression of pre-trained transformers. Adv. Neural. Inf. Process. Syst. 33, 5776\u20135788 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Wu, K., Wu, E., Zou, J.: ClashEval: quantifying the tug-of-war between an LLM\u2019s internal prior and external evidence (2024), https:\/\/arxiv.org\/abs\/2404.10198","DOI":"10.52202\/079017-1053"},{"key":"1_CR39","unstructured":"Xiao, S., Liu, Z., Zhang, P., Muennighoff, N.: C-Pack: packaged resources to advance general Chinese embedding (2023)"},{"key":"1_CR40","unstructured":"Xu, H., et al.: Large language models for cyber security: a systematic literature review (2024). https:\/\/arxiv.org\/abs\/2405.04760"},{"key":"1_CR41","unstructured":"Yu, J., et\u00a0al.: KoLA: carefully benchmarking world knowledge of large language models. arXiv preprint arXiv:2306.09296 (2023)"}],"container-title":["Lecture Notes in Computer Science","Risks and Security of Internet and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-20732-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T10:28:58Z","timestamp":1784024938000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-20732-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032207319","9783032207326"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-20732-6_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CRiSIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Risks and Security of Internet and Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gatineau, QC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"crisis2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/crisis2025.uqo.ca\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}