{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:15:14Z","timestamp":1771467314670,"version":"3.50.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T00:00:00Z","timestamp":1753488000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T00:00:00Z","timestamp":1753488000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100007605","name":"Aarhus Universitet","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100007605","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Minds &amp; Machines"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Accuracy plays an important role in the deployment of machine learning algorithms. But accuracy is not the only epistemic property that matters. For instance, it is well-known that algorithms may perform accurately during their training phase but experience a significant drop in performance when deployed in real-world conditions. To address this gap, people have turned to the concept of algorithmic robustness. Roughly, robustness refers to an algorithm\u2019s ability to maintain its performance across a range of real-world and hypothetical conditions. In this paper, we develop a rigorous account of algorithmic robustness grounded in Robert Nozick\u2019s counterfactual sensitivity and adherence conditions for knowledge. By bridging insights from epistemology and machine learning, we offer a novel conceptualization of robustness that captures key instances of algorithmic brittleness while advancing discussions on reliable AI deployment. We also show how a sensitivity-based account of robustness provides notable advantages over related approaches to algorithmic brittleness, including causal and safety-based ones.<\/jats:p>","DOI":"10.1007\/s11023-025-09734-z","type":"journal-article","created":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T12:09:14Z","timestamp":1753531754000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Counterfactual Account of Algorithmic Robustness"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8755-6746","authenticated-orcid":false,"given":"Jens Christian","family":"Bjerring","sequence":"first","affiliation":[]},{"given":"Jacob","family":"Busch","sequence":"additional","affiliation":[]},{"given":"Lauritz","family":"Aastrup Munch","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"9734_CR1","doi-asserted-by":"crossref","unstructured":"Alcorn, M. A., Li, Q., Gong, Z., Wang, C., Mai, L., Ku, W. S., & Nguyen, A. (2019). Strike (with) a pose: Neural networks are easily fooled by strange poses of familiar objects. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4845\u20134854).","DOI":"10.1109\/CVPR.2019.00498"},{"key":"9734_CR211","doi-asserted-by":"crossref","unstructured":"Bjerring, J. C. (2014). On counterpossibles. Philosophical Studies, 168(2), 327\u2013353.","DOI":"10.1007\/s11098-013-0133-7"},{"key":"9734_CR2","doi-asserted-by":"crossref","unstructured":"Bowie, G. L. (1979). The similarity approach to counterfactuals: Some problems. No\u00fbs, 477\u2013498.","DOI":"10.2307\/2215340"},{"key":"9734_CR3","unstructured":"Cartella, F., Anunciacao, O., Funabiki, Y., Yamaguchi, D., Akishita, T., & Elshocht, O. (2021). Adversarial attacks for tabular data: Application to fraud detection and imbalanced data. arXiv preprint arXiv:2101.08030."},{"key":"9734_CR4","doi-asserted-by":"crossref","unstructured":"Costa, J. C., Roxo, T., Proen\u00e7a, H., & In\u00e1cio, P. R. (2024). How deep learning sees the world: A survey on adversarial attacks & defenses. IEEE Access.","DOI":"10.1109\/ACCESS.2024.3395118"},{"key":"9734_CR611","unstructured":"Elsayed, G., Shankar, S., Cheung, B., Papernot, N., Kurakin, A., Goodfellow, I., & Sohl-Dickstein, J. (2018). Adversarial examples that fool both computer vision and time-limited humans. Advances in Neural Information Processing Systems, 31."},{"key":"9734_CR5","unstructured":"Engstrom, L., Tran, B., Tsipras, D., Schmidt, L., & Madry, A. (2019). Exploring the landscape of spatial robustness. International conference on machine learning (pp. 1802\u20131811). PMLR."},{"key":"9734_CR6","doi-asserted-by":"crossref","unstructured":"Eykholt, K., Evtimov, I., Fernandes, E., Li, B., Rahmati, A., Xiao, C., & Song, D. (2018). Robust physical-world attacks on deep learning visual classification. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1625\u20131634).","DOI":"10.1109\/CVPR.2018.00175"},{"issue":"6433","key":"9734_CR7","doi-asserted-by":"publisher","first-page":"1287","DOI":"10.1126\/science.aaw4399","volume":"363","author":"SG Finlayson","year":"2019","unstructured":"Finlayson, S. G., Bowers, J. D., Ito, J., Zittrain, J. L., Beam, A. L., & Kohane, I. S. (2019). Adversarial attacks on medical machine learning. Science, 363(6433), 1287\u20131289.","journal-title":"Science"},{"key":"9734_CR8","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s11229-023-04334-9","volume":"202","author":"T Freiesleben","year":"2023","unstructured":"Freiesleben, T., & Grote, T. (2023). Beyond generalization: A theory of robustness in machine learning. Synthese, 202, 109.","journal-title":"Synthese"},{"key":"9734_CR911","doi-asserted-by":"crossref","unstructured":"Geirhos, R., Jacobsen, J. H., Michaelis, C., Zemel, R., Brendel, W., Bethge, M., & Wichmann, F. A. (2020). Shortcut learning in deep neural networks. Nature Machine Intelligence, 2(11), 665\u2013673.","DOI":"10.1038\/s42256-020-00257-z"},{"key":"9734_CR9","unstructured":"Geirhos, R., Temme, C. R., Rauber, J., Sch\u00fctt, H. H., Bethge, M., & Wichmann, F. A. (2018). Generalisation in humans and deep neural networks. Advances in Neural Information Processing Systems, 31."},{"issue":"14s","key":"9734_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3593042","volume":"55","author":"S Goyal","year":"2023","unstructured":"Goyal, S., Doddapaneni, S., Khapra, M. M., & Ravindran, B. (2023). A survey of adversarial defenses and robustness in NLP. ACM Computing Surveys, 55(14s), 1\u201339.","journal-title":"ACM Computing Surveys"},{"key":"9734_CR13","doi-asserted-by":"publisher","unstructured":"Grote, T. (2024). Machine learning in healthcare and the methodological priority of epistemology over ethics. Inquiry: A Journal of Medical Care Organization, Provision and Financing, 1\u201330. https:\/\/doi.org\/10.1080\/0020174X.2024.2312207","DOI":"10.1080\/0020174X.2024.2312207"},{"key":"9734_CR12","doi-asserted-by":"publisher","unstructured":"Grote, T., Genin, K., & Sullivan, E. (2024). Reliability in machine learning. Philosophy Compass, e12974. https:\/\/doi.org\/10.1111\/phc3.12974","DOI":"10.1111\/phc3.12974"},{"key":"9734_CR14","doi-asserted-by":"publisher","first-page":"200461","DOI":"10.1016\/j.iswa.2024.200461","volume":"25","author":"Z He","year":"2025","unstructured":"He, Z., Ouyang, C., Alzubaidi, L., Barros, A., & Moreira, C. (2025). Investigating imperceptibility of adversarial attacks on tabular data: An empirical analysis. Intelligent Systems with Applications, 25, 200461.","journal-title":"Intelligent Systems with Applications"},{"key":"9734_CR15","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., & Song, D. (2021). Natural adversarial examples. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 15262\u201315271).","DOI":"10.1109\/CVPR46437.2021.01501"},{"issue":"3","key":"9734_CR18","doi-asserted-by":"publisher","first-page":"2061","DOI":"10.1007\/s11229-019-02192-y","volume":"198","author":"J Landgrebe","year":"2021","unstructured":"Landgrebe, J., & Smith, B. (2021). Making AI meaningful again. Synthese, 198(3), 2061\u20132081.","journal-title":"Synthese"},{"key":"9734_CR20","unstructured":"Lewis, D. (1973). Counterfactuals. Blackwell."},{"key":"9734_CR19","unstructured":"Lewis, D. (1986). On the plurality of worlds. Basil Blackwell."},{"issue":"1","key":"9734_CR16","doi-asserted-by":"publisher","first-page":"9749","DOI":"10.1038\/s41598-024-59783-0","volume":"14","author":"NM Mahmoud","year":"2024","unstructured":"Mahmoud, N. M., & Soliman, A. M. (2024). Early automated detection system for skin cancer diagnosis using artificial intelligent techniques. Scientific Reports, 14(1), 9749.","journal-title":"Scientific Reports"},{"issue":"1","key":"9734_CR17","doi-asserted-by":"publisher","first-page":"6877","DOI":"10.1038\/s41598-022-10526-z","volume":"12","author":"T Makino","year":"2022","unstructured":"Makino, T., Jastrz\u0119bski, S., Oleszkiewicz, W., Chacko, C., Ehrenpreis, R., Samreen, N., & Geras, K. J. (2022). Differences between human and machine perception in medical diagnosis. Scientific Reports, 12(1), 6877.","journal-title":"Scientific Reports"},{"key":"9734_CR21","unstructured":"Nozick, R. (1981). Philosophical explanations. Cambridge University Press."},{"key":"9734_CR22","doi-asserted-by":"crossref","unstructured":"Papasavva, A., Johnson, S., Lowther, E., Lundrigan, S., Mariconti, E., Markovska, A., & Tuptuk, N. (2024). Application of AI-based Models for Online Fraud Detection and Analysis. arXiv preprint arXiv:2409.19022.","DOI":"10.1186\/s40163-025-00248-8"},{"issue":"4","key":"9734_CR23","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1007\/s13042-021-01435-0","volume":"13","author":"A Pedraza","year":"2022","unstructured":"Pedraza, A., Deniz, O., & Bueno, G. (2022). Really natural adversarial examples. International Journal of Machine Learning and Cybernetics, 13(4), 1065\u20131077.","journal-title":"International Journal of Machine Learning and Cybernetics"},{"key":"9734_CR24","doi-asserted-by":"crossref","unstructured":"Stalnaker, R. C. (1968). A theory of conditionals. Ifs: Conditionals, belief, decision, chance and time (pp. 41\u201355). Springer Netherlands.","DOI":"10.1007\/978-94-009-9117-0_2"},{"key":"9734_CR26","unstructured":"Vandenburgh, J. (2023). Machine Learning and Knowledge: Why Robustness Matters. arXiv preprint arXiv:2310.19819."},{"issue":"1","key":"9734_CR27","doi-asserted-by":"publisher","first-page":"4933","DOI":"10.1038\/s41467-023-40499-0","volume":"14","author":"V Veerabadran","year":"2023","unstructured":"Veerabadran, V., Goldman, J., Shankar, S., Cheung, B., Papernot, N., Kurakin, A., & Elsayed, G. F. (2023). Subtle adversarial image manipulations influence both human and machine perception. Nature Communications, 14(1), 4933.","journal-title":"Nature Communications"},{"key":"9734_CR28","doi-asserted-by":"crossref","unstructured":"Vredenburgh, K. (2023). AI and bureaucratic discretion. Inquiry, 1\u201330.","DOI":"10.1080\/0020174X.2023.2261468"},{"key":"9734_CR29","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1007\/s10618-018-0554-1","volume":"32","author":"GI Webb","year":"2018","unstructured":"Webb, G. I., Lee, L. K., Goethals, B., et al. (2018). Analyzing concept drift and shift from sample data. Data Mining and Knowledge Discovery, 32, 1179\u20131199. https:\/\/doi.org\/10.1007\/s10618-018-0554-1","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"10","key":"9734_CR31","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1001\/jamadermatol.2019.1735","volume":"155","author":"JK Winkler","year":"2019","unstructured":"Winkler, J. K., Fink, C., Toberer, F., Enk, A., Deinlein, T., Hofmann-Wellenhof, R., & Haenssle, H. A. (2019). Association between surgical skin markings in dermoscopic images and diagnostic performance of a deep learning convolutional neural network for melanoma recognition. JAMA Dermatology, 155(10), 1135\u20131141.","journal-title":"JAMA Dermatology"},{"key":"9734_CR32","doi-asserted-by":"crossref","unstructured":"Woodward, J. (2005). Making things happen: A theory of causal explanation. Oxford University Press.","DOI":"10.1093\/0195155270.001.0001"},{"key":"9734_CR33","doi-asserted-by":"crossref","unstructured":"Woodward, J. (2021). Causation with a human face: Normative theory and descriptive psychology. Oxford University Press.","DOI":"10.1093\/oso\/9780197585412.001.0001"},{"issue":"12","key":"9734_CR25","doi-asserted-by":"publisher","first-page":"7165","DOI":"10.1007\/s10115-024-02199-z","volume":"66","author":"G Yigit","year":"2024","unstructured":"Yigit, G., & Amasyali, M. F. (2024). From text to multimodal: A survey of adversarial example generation in question answering systems. Knowledge and Information Systems, 66(12), 7165\u20137204.","journal-title":"Knowledge and Information Systems"},{"issue":"11","key":"9734_CR34","doi-asserted-by":"publisher","first-page":"e1002683","DOI":"10.1371\/journal.pmed.1002683","volume":"15","author":"JR Zech","year":"2018","unstructured":"Zech, J. R., Badgeley, M. A., Liu, M., Costa, A. B., Titano, J. J., & Oermann, E. K. (2018). Variable generalization performance of A deep learning model to detect pneumonia in chest radiographs: A cross-sectional study. PLoS Medicine, 15(11), e1002683.","journal-title":"PLoS Medicine"},{"key":"9734_CR35","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/s11023-021-09583-6","volume":"32","author":"C Zednik","year":"2022","unstructured":"Zednik, C., & Boelsen, H. (2022). Scientific exploration and explainable artificial intelligence. Minds & Machines, 32, 219\u2013239.","journal-title":"Minds & Machines"}],"container-title":["Minds and Machines"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11023-025-09734-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11023-025-09734-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11023-025-09734-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T02:56:03Z","timestamp":1758164163000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11023-025-09734-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,26]]},"references-count":36,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["9734"],"URL":"https:\/\/doi.org\/10.1007\/s11023-025-09734-z","relation":{},"ISSN":["1572-8641"],"issn-type":[{"value":"1572-8641","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,26]]},"assertion":[{"value":"16 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}],"article-number":"34"}}