{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T08:56:30Z","timestamp":1769158590919,"version":"3.49.0"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031563256","type":"print"},{"value":"9783031563263","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-56326-3_22","type":"book-chapter","created":{"date-parts":[[2024,4,23]],"date-time":"2024-04-23T07:02:12Z","timestamp":1713855732000},"page":"307-320","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Machine Learning Metrics for\u00a0Network Datasets Evaluation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4737-8735","authenticated-orcid":false,"given":"Dominik","family":"Soukup","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7339-4803","authenticated-orcid":false,"given":"Daniel","family":"Uh\u0159\u00ed\u010dek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0616-4340","authenticated-orcid":false,"given":"Daniel","family":"Va\u0161ata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7794-9511","authenticated-orcid":false,"given":"Tom\u00e1\u0161","family":"\u010cejka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,4,24]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, B., McGrew, D.: Machine learning for encrypted malware traffic classification: accounting for noisy labels and non-stationarity. In: 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2017)","DOI":"10.1145\/3097983.3098163"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Brabec, J., et\u00a0al.: On model evaluation under non-constant class imbalance. In: Computational Science (ICCS) (2020)","DOI":"10.1007\/978-3-030-50423-6_6"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Celdr\u00e1n, A.H., et\u00a0al.: RITUAL: a platform quantifying the trustworthiness of supervised machine learning. In: 18th International Conference on Network and Service Management (CNSM) (2022)","DOI":"10.23919\/CNSM55787.2022.9965139"},{"key":"22_CR4","unstructured":"Chen, H., et\u00a0al.: Data curation and quality assurance for machine learning-based cyber intrusion detection (2021)"},{"key":"22_CR5","unstructured":"Zelaya, C.V.G.: Towards explaining the effects of data preprocessing on machine learning. In: 35th International Conference on Data Engineering (2019)"},{"key":"22_CR6","unstructured":"Hwang, I., et\u00a0al.: SimEX: express prediction of inter-dataset similarity by a fleet of autoencoders. arXiv preprint arXiv:2001.04893 (2020)"},{"key":"22_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2022.108310","volume":"42","author":"K Je\u0159\u00e1bek","year":"2022","unstructured":"Je\u0159\u00e1bek, K., Hynek, K., \u010cejka, T., Ry\u0161av\u00fd, O.: Collection of datasets with DNS over https traffic. Data Brief 42, 108310 (2022)","journal-title":"Data Brief"},{"key":"22_CR8","unstructured":"Koh, P.W., et\u00a0al.: WILDS: a benchmark of in-the-wild distribution shifts. In: Proceedings of the 38th International Conference on Machine Learning (2021)"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Komorniczak, J., Ksieniewicz, P.: Problexity - an open-source python library for binary classification problem complexity assessment. arXiv preprint arXiv:2207.06709 (2022)","DOI":"10.1016\/j.neucom.2022.11.056"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Lanvin, M., et\u00a0al.: Errors in the CICIDS2017 dataset and the significant differences in detection performances it makes (2023). https:\/\/hal.science\/hal-03775466","DOI":"10.1007\/978-3-031-31108-6_2"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Lee, Y.W., et\u00a0al.: AIMQ: a methodology for information quality assessment. Inf. Manag. (2002)","DOI":"10.1016\/S0378-7206(02)00043-5"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Lorena, A.C., Garcia, L.P.F., Lehmann, J., Souto, M.C.P., Ho, T.K.: How complex is your classification problem? A survey on measuring classification complexity. ACM Comput. Surv. 52(5) (2019)","DOI":"10.1145\/3347711"},{"key":"22_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2022.109467","volume":"220","author":"J Luxemburk","year":"2023","unstructured":"Luxemburk, J., \u010cejka, T.: Fine-grained TLS services classification with reject option. Comput. Netw. 220, 109467 (2023)","journal-title":"Comput. Netw."},{"key":"22_CR14","doi-asserted-by":"publisher","first-page":"87918","DOI":"10.1109\/ACCESS.2020.2991800","volume":"8","author":"J Maillo","year":"2020","unstructured":"Maillo, J., Triguero, I., Herrera, F.: Redundancy and complexity metrics for big data classification: towards smart data. IEEE Access 8, 87918\u201387928 (2020)","journal-title":"IEEE Access"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Obaid, H.S., et\u00a0al.: The impact of data pre-processing techniques and dimensionality reduction on the accuracy of machine learning. In: 9th Annual Information Technology, Electromechanical Engineering and Microelectronics Conference (IEMECON) (2019)","DOI":"10.1109\/IEMECONX.2019.8877011"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Papadogiannaki, E., Ioannidis, S.: A survey on encrypted network traffic analysis applications, techniques, and countermeasures. ACM Comput. Surv. 54(6) (2021)","DOI":"10.1145\/3457904"},{"key":"22_CR17","unstructured":"Pendlebury, F., et\u00a0al.: TESSERACT: eliminating experimental bias in malware classification across space and time. In: Proceedings of the 28th USENIX Conference on Security Symposium, USA (2019)"},{"issue":"2","key":"22_CR18","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1007\/s11222-011-9261-0","volume":"22","author":"F Pesarin","year":"2012","unstructured":"Pesarin, F., Salmaso, L.: A review and some new results on permutation testing for multivariate problems. Stat. Comput. 22(2), 639\u2013646 (2012)","journal-title":"Stat. Comput."},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Sharafaldin, I., Lashkari, A.H., Ghorbani, A.A.: Toward generating a new intrusion detection dataset and intrusion traffic characterization. In: International Conference on Information Systems Security and Privacy (2018)","DOI":"10.5220\/0006639801080116"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Soukup, D., et\u00a0al.: Towards evaluating quality of datasets for network traffic domain. In: 17th International Conference on Network and Service Management (CNSM) (2021)","DOI":"10.23919\/CNSM52442.2021.9615601"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Wasielewska, K., et\u00a0al.: Dataset quality assessment with permutation testing showcased on network traffic datasets (2022). http:\/\/dx.doi.org\/10.36227\/techrxiv.20145539.v1","DOI":"10.36227\/techrxiv.20145539.v1"},{"key":"22_CR22","unstructured":"Yoon, J., Arik, S., Pfister, T.: Data valuation using reinforcement learning. In: Daum\u00e9, H., III., Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 119, pp. 10842\u201310851. PMLR (2020)"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhao, S., Sang, Y.: Towards unknown traffic identification using deep auto-encoder and constrained clustering. In: Computational Science \u2013 ICCS (2019)","DOI":"10.1007\/978-3-030-22734-0_23"}],"container-title":["IFIP Advances in Information and Communication Technology","ICT Systems Security and Privacy Protection"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-56326-3_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,23]],"date-time":"2024-04-23T07:07:21Z","timestamp":1713856041000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-56326-3_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031563256","9783031563263"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-56326-3_22","relation":{},"ISSN":["1868-4238","1868-422X"],"issn-type":[{"value":"1868-4238","type":"print"},{"value":"1868-422X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"24 April 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SEC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on ICT Systems Security and Privacy Protection","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Poznan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Poland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 June 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 June 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sec2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ifipsec2023.psnc.pl\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"84","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"26","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}