{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T21:05:15Z","timestamp":1781211915746,"version":"3.54.1"},"reference-count":41,"publisher":"Association for Computing Machinery (ACM)","issue":"CoNEXT2","funder":[{"name":"AI4CTI FISA","award":["FISA-2023-00168"],"award-info":[{"award-number":["FISA-2023-00168"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Netw."],"published-print":{"date-parts":[[2026,6,1]]},"abstract":"<jats:p>Machine learning has given encrypted traffic classification a new momentum. Yet, once deployed, models often fail due to hidden shortcut features, i.e., spurious correlations learned from training data that do not hold in new environments. Prior work has shown their negative impact through costly manual intervention. Here, we present ShortcutCatcher, an automated, model-agnostic framework that detects and mitigates shortcuts with the help of explainable AI. The key idea is to contrast model behaviour on two datasets: a large training dataset and a separate verification dataset that differs in scenario but shares the same feature schema. ShortcutCatcher integrates feature explanation with cross-scenario evaluation in a closed loop, iteratively removing those critical features that would not be valid in deployment. Across multiple encrypted traffic classification tasks and model architectures, ShortcutCatcher uncovers shortcut dependencies and improves cross-scenario generalisation, up to three times over standard training. In addition, ShortcutCatcher exposes dataset limitations where collection artefacts act as silent shortcuts that have gone so far unnoticed, allowing us to finally expose realistic performance without assuming that the underlying task is intrinsically easy<\/jats:p>","DOI":"10.1145\/3808671","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T20:45:46Z","timestamp":1780346746000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ShortcutCatcher: Making Traffic Classification Reliable"],"prefix":"10.1145","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8221-6376","authenticated-orcid":false,"given":"Yuqi","family":"Zhao","sequence":"first","affiliation":[{"name":"Politecnico di Torino, Torino, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3144-9065","authenticated-orcid":false,"given":"Matteo","family":"Boffa","sequence":"additional","affiliation":[{"name":"Politecnico di Torino, Torino, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2920-1856","authenticated-orcid":false,"given":"Luca","family":"Vassio","sequence":"additional","affiliation":[{"name":"Politecnico di Torino, Torino, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1859-6693","authenticated-orcid":false,"given":"Marco","family":"Mellia","sequence":"additional","affiliation":[{"name":"Politecnico di Torino, Torino, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,1]]},"reference":[{"key":"e_1_2_1_1_1","first-page":"3971","volume-title":"31st USENIX Security Symposium (USENIX Security 22)","author":"Arp Daniel","year":"2022","unstructured":"Daniel Arp, Erwin Quiring, Feargus Pendlebury, Alexander Warnecke, Fabio Pierazzi, Christian Wressnegger, Lorenzo Cavallaro, and Konrad Rieck. 2022. Dos and don'ts of machine learning in computer security. In 31st USENIX Security Symposium (USENIX Security 22). 3971-3988."},{"key":"e_1_2_1_2_1","volume-title":"Random forests. Machine learning","author":"Breiman Leo","year":"2001","unstructured":"Leo Breiman. 2001. Random forests. Machine learning, Vol. 45, 1 (2001), 5-32."},{"key":"e_1_2_1_3_1","volume-title":"Breaking Out from the TESSERACT: Reassessing ML-based Malware Detection under Spatio-Temporal Drift. arXiv preprint arXiv:2506.23814","author":"Chow Theo","year":"2025","unstructured":"Theo Chow, Mario D'Onghia, Lorenz Linhardt, Zeliang Kan, Daniel Arp, Lorenzo Cavallaro, and Fabio Pierazzi. 2025. Breaking Out from the TESSERACT: Reassessing ML-based Malware Detection under Spatio-Temporal Drift. arXiv preprint arXiv:2506.23814 (2025)."},{"key":"e_1_2_1_4_1","first-page":"1","article-title":"Explaining by removing: A unified framework for model explanation","volume":"22","author":"Covert Ian","year":"2021","unstructured":"Ian Covert, Scott Lundberg, and Su-In Lee. 2021. Explaining by removing: A unified framework for model explanation. Journal of Machine Learning Research, Vol. 22, 209 (2021), 1-90.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_1_5_1","volume-title":"Understanding global feature contributions with additive importance measures. Advances in neural information processing systems","author":"Covert Ian","year":"2020","unstructured":"Ian Covert, Scott M Lundberg, and Su-In Lee. 2020. Understanding global feature contributions with additive importance measures. Advances in neural information processing systems, Vol. 33 (2020), 17212-17223."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2012.6135854"},{"key":"e_1_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Rudresh Dwivedi Devam Dave Het Naik Smiti Singhal Rana Omer Pankesh Patel Bin Qian Zhenyu Wen Tejal Shah Graham Morgan et al. 2023. Explainable AI (XAI): Core ideas techniques and solutions. ACM computing surveys Vol. 55 9 (2023) 1-33.","DOI":"10.1145\/3561048"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3704742.3704961"},{"key":"e_1_2_1_9_1","volume-title":"Autogluon-tabular: Robust and accurate automl for structured data. arXiv preprint arXiv:2003.06505","author":"Erickson Nick","year":"2020","unstructured":"Nick Erickson, Jonas Mueller, Alexander Shirkov, Hang Zhang, Pedro Larroy, Mu Li, and Alexander Smola. 2020. Autogluon-tabular: Robust and accurate automl for structured data. arXiv preprint arXiv:2003.06505 (2020)."},{"key":"e_1_2_1_10_1","unstructured":"OpenAI et al. 2024. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL] https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2013.100613.00161"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP60621.2024.00042"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00612-w"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"e_1_2_1_15_1","first-page":"407","volume-title":"Proceedings of the 2nd international conference on information systems security and privacy (ICISSP","author":"Gil Gerard Drapper","year":"2016","unstructured":"Gerard Drapper Gil, Arash Habibi Lashkari, Mohammad Mamun, and Ali A Ghorbani. 2016. Characterization of encrypted and VPN traffic using time-related features. In Proceedings of the 2nd international conference on information systems security and privacy (ICISSP 2016). SciTePress Set\u00fabal, Portugal, 407-414."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3560609"},{"key":"e_1_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Van Jacobson Robert Braden and Dave Borman. 1992. RFC1323: TCP extensions for high performance.","DOI":"10.17487\/rfc1323"},{"key":"e_1_2_1_18_1","volume-title":"Wrappers for feature subset selection. Artificial intelligence","author":"Kohavi Ron","year":"1997","unstructured":"Ron Kohavi and George H John. 1997. Wrappers for feature subset selection. Artificial intelligence, Vol. 97, 1-2 (1997), 273-324."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3574971"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512217"},{"key":"e_1_2_1_21_1","volume-title":"A unified approach to interpreting model predictions. Advances in neural information processing systems","author":"Lundberg Scott M","year":"2017","unstructured":"Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3504955"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2674005.2674991"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2008.080406"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2883147"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3457904"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3754341"},{"key":"e_1_2_1_28_1","first-page":"729","volume-title":"28th USENIX Security Symposium (USENIX Security 19)","author":"Pendlebury Feargus","year":"2019","unstructured":"Feargus Pendlebury, Fabio Pierazzi, Roberto Jordaney, Johannes Kinder, and Lorenzo Cavallaro. 2019. TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time. In 28th USENIX Security Symposium (USENIX Security 19). USENIX Association, Santa Clara, CA, 729-746. https:\/\/www.usenix.org\/conference\/usenixsecurity19\/presentation\/pendlebury"},{"key":"e_1_2_1_29_1","volume-title":"Marco Tulio Ribeiro, and Ameet Talwalkar","author":"Plumb Gregory","year":"2021","unstructured":"Gregory Plumb, Marco Tulio Ribeiro, and Ameet Talwalkar. 2021. Finding and fixing spurious patterns with explanations. arXiv preprint arXiv:2106.02112 (2021)."},{"key":"e_1_2_1_30_1","volume-title":"TabICL: A Tabular Foundation Model for In-Context Learning on Large Data. In International Conference on Machine Learning.","author":"Qu Jingang","year":"2025","unstructured":"Jingang Qu, David Holzm\u00fcller, Ga\u00ebl Varoquaux, and Marine Le Morvan. 2025a. TabICL: A Tabular Foundation Model for In-Context Learning on Large Data. In International Conference on Machine Learning."},{"key":"e_1_2_1_31_1","volume-title":"TabICL: A Tabular Foundation Model for In-Context Learning on Large Data. In International Conference on Machine Learning.","author":"Qu Jingang","year":"2025","unstructured":"Jingang Qu, David Holzm\u00fcller, Ga\u00ebl Varoquaux, and Marine Le Morvan. 2025b. TabICL: A Tabular Foundation Model for In-Context Learning on Large Data. In International Conference on Machine Learning."},{"key":"e_1_2_1_32_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1800819"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2023.3282740"},{"key":"e_1_2_1_35_1","volume-title":"Navigating shortcuts, spurious correlations, and confounders: From origins via detection to mitigation. arXiv preprint arXiv:2412.05152","author":"Steinmann David","year":"2024","unstructured":"David Steinmann, Felix Divo, Maurice Kraus, Antonia W\u00fcst, Lukas Struppek, Felix Friedrich, and Kristian Kersting. 2024. Navigating shortcuts, spurious correlations, and confounders: From origins via detection to mitigation. arXiv preprint arXiv:2412.05152 (2024)."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314293"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.2967588"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP61157.2025.00165"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3727063.3727067"},{"key":"e_1_2_1_40_1","volume-title":"International Conference on Machine Learning. PMLR, 37765-37786","author":"Wu Shirley","year":"2023","unstructured":"Shirley Wu, Mert Yuksekgonul, Linjun Zhang, and James Zou. 2023. Discover and cure: Concept-aware mitigation of spurious correlation. In International Conference on Machine Learning. PMLR, 37765-37786."},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750498"}],"container-title":["Proceedings of the ACM on Networking"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3808671","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T20:21:30Z","timestamp":1781209290000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3808671"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,1]]},"references-count":41,"journal-issue":{"issue":"CoNEXT2","published-print":{"date-parts":[[2026,6,1]]}},"alternative-id":["10.1145\/3808671"],"URL":"https:\/\/doi.org\/10.1145\/3808671","relation":{},"ISSN":["2834-5509"],"issn-type":[{"value":"2834-5509","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,1]]},"assertion":[{"value":"2026-06-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}