{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T21:19:59Z","timestamp":1782940799493,"version":"3.54.5"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.23919\/cnsm67658.2025.11297526","type":"proceedings-article","created":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T18:40:10Z","timestamp":1766428810000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["Irreconcilable Differences? Investigating Consensus of Post-hoc XAI for ML-NIDS via Decomposition"],"prefix":"10.23919","author":[{"given":"Katharina","family":"Dietz","sequence":"first","affiliation":[{"name":"University of Würzburg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johannes","family":"Schleicher","sequence":"additional","affiliation":[{"name":"University of Augsburg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Gei\u00dfler","sequence":"additional","affiliation":[{"name":"University of Würzburg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Seufert","sequence":"additional","affiliation":[{"name":"University of Augsburg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Ho\u00dffeld","sequence":"additional","affiliation":[{"name":"University of Würzburg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2018.11.001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP57164.2023.00042"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2024.3382393"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3406939"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2870052"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10088-y"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref8","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017","journal-title":"NeurIPS"},{"key":"ref9","article-title":"Learning important features through propagating activation differences","author":"Shrikumar","year":"2017","journal-title":"ICML"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/CNSM62983.2024.10814448"},{"key":"ref11","article-title":"The disagreement problem in explainable machine learning: A practitioner\u2019s perspective","author":"Krishna","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref12","article-title":"Disagreement amongst counterfactual explanations: How transparency can be deceptive","author":"Brughmans","year":"2024","journal-title":"Trans. Oper. Res. (TOP)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92648-8_15"},{"key":"ref14","article-title":"I choose you: Evaluating the impact of feature selection on XAI consensus for ML-NIDS","author":"Dietz","year":"2025","journal-title":"MaLeNe"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.6028\/nist.sp.800-35"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v38i3.2741"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/ett.4970"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2023.1099521"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1515\/9781400881970-018"},{"key":"ref20","article-title":"EXAGREE: Towards explanation agreement in explainable machine learning","author":"Li","year":"2024","journal-title":"arXiv:2411.01956"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00159"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP48549.2020.00018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSPW61312.2024.00067"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3600160.3600193"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME55016.2022.00056"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP57164.2023.00022"},{"key":"ref27","article-title":"Comparing explanation methods for traditional machine learning models part 1: an overview of current methods and quantifying their disagreement","author":"Flora","year":"2022","journal-title":"arXiv:2211.08943"},{"key":"ref28","article-title":"Comparing explanation methods for traditional machine learning models part 2: Quantifying model explainability faithfulness and improvements with dimensionality reduction","author":"Flora","year":"2022","journal-title":"arXiv:2211.10378"},{"key":"ref29","article-title":"Understanding the size of the feature importance disagreement problem in real-world data","volume-title":"ICML Workshop IMLH","author":"Markus"},{"key":"ref30","article-title":"Unifying feature-based explanations with functional ANOVA and cooperative game theory","author":"Fumagalli","year":"2025","journal-title":"AISTATS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11416-022-00441-2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2988359"},{"key":"ref33","article-title":"XAI-based feature selection for improved network intrusion detection systems","author":"Arreche","year":"2024","journal-title":"arXiv:2410.10050"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3048038"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3655693.3655714"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3365140"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2025.101505"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59491-6_40"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-44064-9_25"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5220\/0012475200003636"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-022-00840-5"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10952-7"},{"key":"ref43","article-title":"AGREE: A feature attribution aggregation framework to address explainer disagreements with alignment metrics","volume-title":"CEUR Workshop Proc.","author":"Pirie"},{"key":"ref44","article-title":"Can we agree? on the Rash\u00f4mon effect and the reliability of post-hoc explainable AI","author":"Poiret","year":"2023","journal-title":"arXiv:2308.07247"},{"key":"ref45","article-title":"Which explanation should I choose? A function approximation perspective to characterizing post hoc explanations","author":"Han","year":"2022","journal-title":"NeurIPS"},{"key":"ref46","article-title":"Fighting the disagreement in explainable machine learning with consensus","author":"Banegas-Luna","year":"2023","journal-title":"arXiv:2307.01288"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604687"},{"key":"ref48","article-title":"Tackling the XAI disagreement problem with regional explanations","author":"Laberge","year":"2024","journal-title":"AISTATS"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-79035-5_12"},{"key":"ref50","article-title":"Evaluating the explainers: black-box explainable machine learning for student success prediction in MOOCs","volume-title":"Int. Conf. Educ. Data Min. (EDM)","author":"Swamy"},{"key":"ref51","article-title":"How well do feature-additive explainers explain feature-additive predictors?","volume-title":"NeurIPS Workshop XAIA","author":"Carmichael"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63800-8_13"},{"key":"ref53","article-title":"Exploring the relationship between feature attribution methods and model performance","volume-title":"AAAI Workshop AI4ED","author":"Silva"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5220\/0006639801080116"},{"key":"ref55","article-title":"Flow-based benchmark data sets for intrusion detection","volume-title":"Eur. Conf. Cyber Warf. Secur. (ECCWS)","author":"Ring"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3165809"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref58","article-title":"Prince: Python factor analysis library","author":"Halford"},{"key":"ref59","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"NeurIPS"}],"event":{"name":"2025 21st International Conference on Network and Service Management (CNSM)","location":"Bologna, Italy","start":{"date-parts":[[2025,10,27]]},"end":{"date-parts":[[2025,10,31]]}},"container-title":["2025 21st International Conference on Network and Service Management (CNSM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11297200\/11297407\/11297526.pdf?arnumber=11297526","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T06:20:56Z","timestamp":1766470856000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11297526\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":59,"URL":"https:\/\/doi.org\/10.23919\/cnsm67658.2025.11297526","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]}}}