{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:17:34Z","timestamp":1761175054020,"version":"build-2065373602"},"reference-count":25,"publisher":"Polish Information Processing Society","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.15439\/2025f5708","type":"proceedings-article","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T07:44:23Z","timestamp":1761119063000},"page":"345-350","source":"Crossref","is-referenced-by-count":0,"title":["Out-Of-Distribution Is Not Magic: The Clash Between Rejection Rate and Model Success"],"prefix":"10.15439","volume":"43","author":[{"given":"Itay","family":"Meiri","sequence":"first","affiliation":[{"name":"Ariel University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2055-2211","authenticated-orcid":true,"given":"Ran","family":"Dubin","sequence":"additional","affiliation":[{"name":"Department of Computer and Software Engineering, Ariel Cyber Innovation Center, Ariel University, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3670-0784","authenticated-orcid":true,"given":"Amit","family":"Dvir","sequence":"additional","affiliation":[{"name":"Department of Computer and Software Engineering, Ariel Cyber Innovation Center, Ariel University, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9940-5654","authenticated-orcid":true,"given":"Chen","family":"Hajaj","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering and Management, Data Science and Artificial Intelligence Research Center"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"6175","published-online":{"date-parts":[[2025,10,15]]},"reference":[{"key":"ref1","unstructured":"D. Moore, K. Keys, R. Koga, E. Lagache, and K. C. Claffy, \u201cThe\n{CoralReef} software suite as a tool for system and network administrators,\u201d in LISA, 2001."},{"key":"ref2","doi-asserted-by":"crossref","unstructured":"S. Xu, J. Han, Y. Liu, H. Liu, and Y. Bai, \u201cFew-shot traffic classification\nbased on autoencoder and deep graph convolutional networks,\u201d Scientific\nReports, vol. 15, no. 1, p. 8995, 2025.","DOI":"10.1038\/s41598-025-94240-6"},{"key":"ref3","doi-asserted-by":"crossref","unstructured":"P. Tang, Y. Dong, S. Mao, H.-L. Wei, and J. Jin, \u201cOnline classification\nof network traffic based on granular computing,\u201d IEEE Transactions on\nSystems, Man, and Cybernetics: Systems, vol. 53, no. 8, pp. 5199\u20135211,\n2023.","DOI":"10.1109\/TSMC.2023.3259543"},{"key":"ref4","unstructured":"L. Yang, A. Finamore, F. Jun, and D. Rossi, \u201cDeep Learning and\nTraffic Classification: Lessons learned from a commercial-grade dataset\nwith hundreds of encrypted and zero-day applications,\u201d arXiv preprint\nhttps:\/\/arxiv.org\/abs\/2104.03182, 2021."},{"key":"ref5","unstructured":"A. Krizhevsky, I. Sutskever, and G. E. Hinton, \u201cImageNet Classification\nwith Deep Convolutional Neural Networks,\u201d in Advances in Neural\nInformation Processing Systems, vol. 25, 2012."},{"key":"ref6","doi-asserted-by":"crossref","unstructured":"X. Wang, Y. Wang, Y. Lai, Z. Hao, and A. X. Liu, \u201cReliable openset network traffic classification,\u201d IEEE Transactions on Information\nForensics and Security, 2025.","DOI":"10.1109\/TIFS.2025.3544067"},{"key":"ref7","unstructured":"S. Vaze, K. Han, A. Vedaldi, and A. Zisserman, \u201cOpen-Set Recognition:\nA good closed-set classifier is all you need,\u201d CoRR, vol. abs\/2110.06207,\n2021. [Online]. Available: https:\/\/arxiv.org\/abs\/2110.06207"},{"key":"ref8","unstructured":"V. Franc, D. Pr\u016f\u0161a, and V. Voracek, \u201cOptimal strategies for\nreject option classifiers,\u201d CoRR, vol. abs\/2101.12523, 2021. [Online].\nAvailable: https:\/\/arxiv.org\/abs\/2101.12523"},{"key":"ref9","doi-asserted-by":"crossref","unstructured":"Z. Fang, J. Lu, and G. Zhang, \u201cOut-of-distribution detection with nonsemantic exploration,\u201d Information Sciences, vol. 705, p. 121989, 2025.","DOI":"10.1016\/j.ins.2025.121989"},{"key":"ref10","doi-asserted-by":"crossref","unstructured":"S. Thulasidasan, S. Thapa, S. Dhaubhadel, G. Chennupati, T. Bhattacharya, and J. Bilmes, \u201cAn effective baseline for robustness to distributional shift,\u201d in ICMLA. IEEE, 2021, pp. 278\u2013285.","DOI":"10.1109\/ICMLA52953.2021.00050"},{"key":"ref11","unstructured":"T. DeVries and G. W. Taylor, \u201cLearning confidence for out-of-distribution detection in neural networks,\u201d arXiv preprint\nhttps:\/\/arxiv.org\/abs\/1802.04865, 2018."},{"key":"ref12","doi-asserted-by":"crossref","unstructured":"Y. Chen, Z. Li, J. Shi, G. Gou, C. Liu, and G. Xiong, \u201cNot Afraid\nof the Unseen: a Siamese Network based Scheme for Unknown Traffic\nDiscovery,\u201d in ISCC, 2020, pp. 1\u20137.","DOI":"10.1109\/ISCC50000.2020.9219734"},{"key":"ref13","doi-asserted-by":"crossref","unstructured":"H. He, Y. Lai, Y. Wang, S. Le, and Z. Zhao, \u201cA data skew-based\nunknown traffic classification approach for TLS applications,\u201d Future\nGeneration Computer Systems, 2022.","DOI":"10.1016\/j.future.2022.08.003"},{"key":"ref14","doi-asserted-by":"crossref","unstructured":"Z. Yang and W. Lin, \u201cUnknown traffic identification based on deep\nadaptation networks,\u201d in 2020 IEEE 45th LCN Symposium on Emerging\nTopics in Networking (LCN Symposium). IEEE, 2020, pp. 10\u201318.","DOI":"10.1109\/LCNSymposium50271.2020.9363263"},{"key":"ref15","unstructured":"S. Liang, Y. Li, and R. Srikant, \u201cEnhancing the reliability of out-of-distribution image detection in neural networks,\u201d arXiv preprint\nhttps:\/\/arxiv.org\/abs\/1706.02690, 2017."},{"key":"ref16","doi-asserted-by":"crossref","unstructured":"L. Neal, M. Olson, X. Fern, W.-K. Wong, and F. Li, \u201cOpen Set Learning\nwith Counterfactual Images,\u201d in European Conference, Munich, Germany, September 8\u201314, 2018, 2018, pp. 620\u2013635.","DOI":"10.1007\/978-3-030-01231-1_38"},{"key":"ref17","doi-asserted-by":"crossref","unstructured":"S. Rezaei and X. Liu, \u201cDeep Learning for Encrypted Traffic Classification: An Overview,\u201d IEEE Communications Magazine, vol. 57, no. 5,\npp. 76\u201381, may 2019.","DOI":"10.1109\/MCOM.2019.1800819"},{"key":"ref18","doi-asserted-by":"crossref","unstructured":"G. Draper-Gil, A. H. Lashkari, M. S. I. Mamun, and A. A. Ghorbani,\n\u201cCharacterization of Encrypted and VPN traffic using time-related\nfeatures,\u201d in ICISSP, Rome, Italy, February 19-21, 2016, pp. 407\u2013414.","DOI":"10.5220\/0005740704070414"},{"key":"ref19","unstructured":"Stratosphere, \u201cStratosphere Laboratory Datasets,\u201d 2015, retrieved March\n13, 2020, from https:\/\/www.stratosphereips.org\/datasets-overview."},{"key":"ref20","unstructured":"R. Dubin, A. Dvir, O. Pele, J. Muehlstein, Y. Zion, M. Bahumi, and\nI. Kirshenboim, \u201cAnalyzing HTTPS Encrypted Traffic to Identify User\u2019s\nOperating System, Browser and Application,\u201d in IEEE CCNC, June\n2017."},{"key":"ref21","doi-asserted-by":"crossref","unstructured":"A. Lichy, O. Bader, R. Dubin, A. Dvir, and C. Hajaj, \u201cWhen a rf\nbeats a cnn and gru, together\u2014a comparison of deep learning and\nclassical machine learning approaches for encrypted malware traffic\nclassification,\u201d Computers & Security, vol. 124, p. 103000, 2023.","DOI":"10.1016\/j.cose.2022.103000"},{"key":"ref22","unstructured":"S. Jorgensen, J. Holodnak, J. Dempsey, K. de Souza, A. Raghunath,\nV. Rivet, N. DeMoes, A. Alejos, and A. Wollaber, \u201cExtensible Machine\nLearning for Encrypted Network Traffic Application Labeling via Uncertainty Quantification,\u201d arXiv preprint https:\/\/arxiv.org\/abs\/2205.05628, 2022."},{"key":"ref23","unstructured":"I. Meiri, \u201cOod not magic - github repository,\u201d 2025, available at: https:\/\/github.com\/ArielCyber\/OOD_Is_Not_Magic."},{"key":"ref24","unstructured":"D. Hendrycks and K. Gimpel, \u201cA baseline for detecting misclassified\nand out-of-distribution examples in neural networks,\u201d arXiv preprint\nhttps:\/\/arxiv.org\/abs\/1610.02136, 2016."},{"key":"ref25","unstructured":"J. Ren, P. J. Liu, E. Fertig, J. Snoek, R. Poplin, M. Depristo, J. Dillon,\nand B. Lakshminarayanan, \u201cLikelihood ratios for out-of-distribution\ndetection,\u201d in Advances in Neural Information Processing Systems,\nvol. 32. Curran Associates, Inc., 2019."}],"event":{"name":"20th Conference on Computer Science and Intelligence Systems (FedCSIS)","theme":"Computer Science and Intelligence Systems","location":"Krak\u00f3w, Poland","acronym":"FedCSIS","number":"20","start":{"date-parts":[[2025,9,14]]},"end":{"date-parts":[[2025,9,17]]}},"container-title":["Annals of Computer Science and Information Systems","Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS)"],"original-title":[],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T07:47:42Z","timestamp":1761119262000},"score":1,"resource":{"primary":{"URL":"https:\/\/annals-csis.org\/Volume_43\/drp\/5708.html"}},"subtitle":[],"proceedings-subject":"Computer Science and Information Systems","short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":25,"URL":"https:\/\/doi.org\/10.15439\/2025f5708","relation":{},"ISSN":["2300-5963"],"issn-type":[{"value":"2300-5963","type":"print"}],"subject":[],"published":{"date-parts":[[2025,10,15]]}}}