{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T11:11:18Z","timestamp":1778152278224,"version":"3.51.4"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032253132","type":"print"},{"value":"9783032253149","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\/978-3-032-25314-9_10","type":"book-chapter","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T10:21:26Z","timestamp":1778149286000},"page":"130-145","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Systematic Evaluation of Synthetic Data Augmentation for Multi-class NetFlow Traffic"],"prefix":"10.1007","author":[{"given":"Maximilian","family":"Wolf","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dieter","family":"Landes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Hotho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Schl\u00f6r","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,8]]},"reference":[{"key":"10_CR1","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein GAN. arXiv (2017)"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Boudegzdame, N., Sedki, K., Tspora, R., Lamy, J.B.: An approach for improving oversampling by filtering out unrealistic synthetic data. In: ICAART (3), pp. 291\u2013298 (2024)","DOI":"10.5220\/0012325400003636"},{"key":"10_CR3","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321\u2013357 (2002)","journal-title":"J. Artif. Intell. Res."},{"key":"10_CR4","doi-asserted-by":"publisher","unstructured":"Chen, T., Guestrin, C.: Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785\u2013794. ACM, San Francisco California USA (2016). https:\/\/doi.org\/10.1145\/2939672.2939785. https:\/\/dl.acm.org\/doi\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"10_CR5","unstructured":"Elkan, C.: The foundations of cost-sensitive learning. In: International Joint Conference on Artificial Intelligence, vol.\u00a017, pp. 973\u2013978. Lawrence Erlbaum Associates Ltd (2001)"},{"key":"10_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114582","volume":"174","author":"J Engelmann","year":"2021","unstructured":"Engelmann, J., Lessmann, S.: Conditional Wasserstein GAN-based oversampling of tabular data for imbalanced learning. Expert Syst. Appl. 174, 114582 (2021). https:\/\/doi.org\/10.1016\/j.eswa.2021.114582","journal-title":"Expert Syst. Appl."},{"key":"10_CR7","unstructured":"ENISA: European union agency for cybersecurity threat landscape 2023 (2023). https:\/\/www.enisa.europa.eu\/publications\/enisa-threat-landscape-2023"},{"key":"10_CR8","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1613\/jair.1.11192","volume":"61","author":"A Fern\u00e1ndez","year":"2018","unstructured":"Fern\u00e1ndez, A., Garcia, S., Herrera, F., Chawla, N.V.: Smote for learning from imbalanced data: progress and challenges, marking the 15-year anniversary. J. Artif. Intell. Res. 61, 863\u2013905 (2018)","journal-title":"J. Artif. Intell. Res."},{"key":"10_CR9","doi-asserted-by":"publisher","unstructured":"Fern\u00e1ndez, A., L\u00f3pez, V., Galar, M., Del Jesus, M.J., Herrera, F.: Analysing the classification of imbalanced data-sets with multiple classes: binarization techniques and ad-hoc approaches. Knowl.-Based Syst. 42, 97\u2013110 (2013). https:\/\/doi.org\/10.1016\/j.knosys.2013.01.018","DOI":"10.1016\/j.knosys.2013.01.018"},{"issue":"1","key":"10_CR10","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","volume":"63","author":"P Geurts","year":"2006","unstructured":"Geurts, P., Ernst, D., Wehenkel, L.: Extremely randomized trees. Mach. Learn. 63(1), 3\u201342 (2006). https:\/\/doi.org\/10.1007\/s10994-006-6226-1","journal-title":"Mach. Learn."},{"issue":"2","key":"10_CR11","doi-asserted-by":"publisher","first-page":"827","DOI":"10.3390\/make6020039","volume":"6","author":"S Gholampour","year":"2024","unstructured":"Gholampour, S.: Impact of nature of medical data on machine and deep learning for imbalanced datasets: clinical validity of smote is questionable. Mach. Learn. Knowl. Extr. 6(2), 827\u2013841 (2024)","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"10_CR12","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"10_CR13","unstructured":"Grandini, M., Bagli, E., Visani, G.: Metrics for multi-class classification: an overview arXiv:2008.05756 (2020). http:\/\/arxiv.org\/abs\/2008.05756"},{"key":"10_CR14","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Guo, Y., Xiong, G., Li, Z., Shi, J., Cui, M., Gou, G.: Combating imbalance in network traffic classification using GAN based oversampling. In: 2021 IFIP Networking Conference (IFIP Networking), pp.\u00a01\u20139 (2021)","DOI":"10.23919\/IFIPNetworking52078.2021.9472777"},{"key":"10_CR16","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1975","volume":"10","author":"\u00d3M Guti\u00e9rrez","year":"2024","unstructured":"Guti\u00e9rrez, \u00d3.M., N\u00fa\u00f1ez, J.C.S., \u00c1vila, M., Caro, A.: A detailed study of resampling algorithms for cyberattack classification in engineering applications. PeerJ Comput. Sci. 10, e1975 (2024). https:\/\/doi.org\/10.7717\/peerj-cs.1975","journal-title":"PeerJ Comput. Sci."},{"key":"10_CR17","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.eswa.2016.12.035","volume":"73","author":"G Haixiang","year":"2017","unstructured":"Haixiang, G., Yijing, L., Shang, J., Mingyun, G., Yuanyue, H., Bing, G.: Learning from class-imbalanced data: review of methods and applications. Expert Syst. Appl. 73, 220\u2013239 (2017). https:\/\/doi.org\/10.1016\/j.eswa.2016.12.035","journal-title":"Expert Syst. Appl."},{"key":"10_CR18","unstructured":"Han, J., Kamber, M., Pei, J.: Data Mining: Concepts and Techniques, 3rd edn. Elsevier\/Morgan Kaufmann, Amsterdam (2012)"},{"key":"10_CR19","doi-asserted-by":"publisher","unstructured":"He, H., Bai, Y., Garcia, E.A., Li, S.: Adasyn: adaptive synthetic sampling approach for imbalanced learning. In: 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), pp. 1322\u20131328. IEEE, Hong Kong, China (2008). https:\/\/doi.org\/10.1109\/IJCNN.2008.4633969. http:\/\/ieeexplore.ieee.org\/document\/4633969\/","DOI":"10.1109\/IJCNN.2008.4633969"},{"issue":"1","key":"10_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3639037","volume":"8","author":"X Jiang","year":"2024","unstructured":"Jiang, X., et al.: Netdiffusion: network data augmentation through protocol-constrained traffic generation. Proc. ACM Measur. Anal. Comput. Syst. 8(1), 1\u201332 (2024). https:\/\/doi.org\/10.1145\/3639037","journal-title":"Proc. ACM Measur. Anal. Comput. Syst."},{"key":"10_CR21","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Laurikkala, J.: Improving identification of difficult small classes by balancing class distribution. In: Quaglini, S., Barahona, P., Andreassen, S. (eds.) Artificial Intelligence in Medicine, pp. 63\u201366. Springer, Heidelberg (2001)","DOI":"10.1007\/3-540-48229-6_9"},{"issue":"2","key":"10_CR23","doi-asserted-by":"publisher","first-page":"1000","DOI":"10.1109\/TR.2022.3164877","volume":"71","author":"C Liu","year":"2022","unstructured":"Liu, C., Antypenko, R., Sushko, I., Zakharchenko, O.: Intrusion detection system after data augmentation schemes based on the VAE and CVAE. IEEE Trans. Reliab. 71(2), 1000\u20131010 (2022). https:\/\/doi.org\/10.1109\/TR.2022.3164877","journal-title":"IEEE Trans. Reliab."},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Liu, X., Li, T., Zhang, R., Wu, D., Liu, Y., Yang, Z.: A GAN and feature selection-based oversampling technique for intrusion detection. Secur. Commun. Networks 2021, 9947059:1\u20139947059:15 (2021)","DOI":"10.1155\/2021\/9947059"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Lo, W.W., Layeghy, S., Sarhan, M., Gallagher, M., Portmann, M.: E-graphsage: a graph neural network based intrusion detection system for IoT. In: NOMS 2022-2022 IEEE\/IFIP Network Operations and Management Symposium, pp.\u00a01\u20139. IEEE (2022)","DOI":"10.1109\/NOMS54207.2022.9789878"},{"key":"10_CR26","unstructured":"Mani, I., Zhang, I.: KNN approach to unbalanced data distributions: a case study involving information extraction. In: Proceedings of Workshop on Learning from Imbalanced Datasets, vol.\u00a0126, pp. 1\u20137. ICML (2003)"},{"key":"10_CR27","doi-asserted-by":"publisher","unstructured":"Moustafa, N., Slay, J.: UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set). In: 2015 Military Communications and Information Systems Conference (MilCIS), pp.\u00a01\u20136 (2015). https:\/\/doi.org\/10.1109\/MilCIS.2015.7348942","DOI":"10.1109\/MilCIS.2015.7348942"},{"key":"10_CR28","unstructured":"Ntop: nprobe 10.1 documentation (2023). https:\/\/www.ntop.org\/guides\/nprobe\/index.html"},{"key":"10_CR29","unstructured":"Pendlebury, F., Pierazzi, F., Jordaney, R., Kinder, J., Cavallaro, L.: Tesseract: eliminating experimental bias in malware classification across space and time. In: USENIX Security Symposium (2018). https:\/\/api.semanticscholar.org\/CorpusID:49905199"},{"key":"10_CR30","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.cose.2018.12.012","volume":"82","author":"M Ring","year":"2018","unstructured":"Ring, M., Schl\u00f6r, D., Landes, D., Hotho, A.: Flow-based network traffic generation using generative adversarial networks. Comput. Secur. 82, 156\u2013172 (2018)","journal-title":"Comput. Secur."},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10_CR32","doi-asserted-by":"publisher","unstructured":"Salman, O., Elhajj, I.H., Kayssi, A., Chehab, A.: A review on machine learning\u2013based approaches for internet traffic classification. Ann. Telecommun. 75(11\u201312), 673\u2013710 (2020). https:\/\/doi.org\/10.1007\/s12243-020-00770-7","DOI":"10.1007\/s12243-020-00770-7"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Sarhan, M., Layeghy, S., Moustafa, N., Portmann, M.: Netflow datasets for machine learning-based network intrusion detection systems. In: Big Data Technologies and Applications: 10th EAI International Conference, BDTA 2020, and 13th EAI International Conference on Wireless Internet, WiCON 2020, Virtual Event, 11 December 2020, Proceedings 10, pp. 117\u2013135. Springer (2021)","DOI":"10.1007\/978-3-030-72802-1_9"},{"key":"10_CR34","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":"10_CR35","unstructured":"Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"issue":"8","key":"10_CR36","doi-asserted-by":"publisher","first-page":"2187","DOI":"10.1007\/s10994-021-06023-5","volume":"110","author":"M Steininger","year":"2021","unstructured":"Steininger, M., Kobs, K., Davidson, P., Krause, A., Hotho, A.: Density-based weighting for imbalanced regression. Mach. Learn. 110(8), 2187\u20132211 (2021). https:\/\/doi.org\/10.1007\/s10994-021-06023-5","journal-title":"Mach. Learn."},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Tavallaee, M., Bagheri, E., Lu, W., Ghorbani, A.A.: A detailed analysis of the KDD cup 99 data set. In: 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications, pp.\u00a01\u20136 (2009)","DOI":"10.1109\/CISDA.2009.5356528"},{"key":"10_CR38","doi-asserted-by":"publisher","unstructured":"Tomek, I.: Two modifications of CNN. IEEE Trans. Syst. Man Cybern. SMC-6(11), 769\u2013772 (1976). https:\/\/doi.org\/10.1109\/TSMC.1976.4309452","DOI":"10.1109\/TSMC.1976.4309452"},{"key":"10_CR39","doi-asserted-by":"publisher","unstructured":"Wilson, D.L.: Asymptotic properties of nearest neighbor rules using edited data. IEEE Trans. Syst. Man Cybern. SMC-2(3), 408\u2013421 (1972). https:\/\/doi.org\/10.1109\/TSMC.1972.4309137","DOI":"10.1109\/TSMC.1972.4309137"},{"key":"10_CR40","doi-asserted-by":"publisher","unstructured":"Wolf, M., Tritscher, J., Landes, D., Hotho, A., Schl\u00f6r, D.: Benchmarking of synthetic network data: reviewing challenges and approaches. Comput. Secur. 103993 (2024). https:\/\/doi.org\/10.1016\/j.cose.2024.103993. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0167404824002980","DOI":"10.1016\/j.cose.2024.103993"}],"container-title":["Communications in Computer and Information Science","Machine Learning and Principles and Practice of Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-25314-9_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T10:21:37Z","timestamp":1778149297000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-25314-9_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032253132","9783032253149"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-25314-9_10","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"8 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vilnius","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}