{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T05:11:20Z","timestamp":1754111480606,"version":"3.37.3"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T00:00:00Z","timestamp":1704758400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T00:00:00Z","timestamp":1704758400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"TAILOR","award":["952215"],"award-info":[{"award-number":["952215"]}]},{"DOI":"10.13039\/501100002347","name":"Federal Ministry of Education and Research","doi-asserted-by":"crossref","award":["FKZ 01IS19081"],"award-info":[{"award-number":["FKZ 01IS19081"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100005714","name":"Technische Universit\u00e4t Darmstadt","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005714","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2024,3]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The recent years have been marked by extended research on adversarial attacks, especially on deep neural networks. With this work we intend on posing and investigating the question of whether the phenomenon might be more general in nature, that is, adversarial-style attacks outside classical classification tasks. Specifically, we investigate optimization problems as they constitute a fundamental part of modern AI research. To this end, we consider the base class of optimizers namely Linear Programs (LPs). On our initial attempt of a na\u00efve mapping between the formalism of adversarial examples and LPs, we quickly identify the key ingredients missing for making sense of a reasonable notion of adversarial examples for LPs. Intriguingly, the formalism of Pearl\u2019s notion to causality allows for the right description of adversarial like examples for LPs. Characteristically, we show the direct influence of the Structural Causal Model (SCM) onto the subsequent LP optimization, which ultimately exposes a notion of confounding in LPs (inherited by said SCM) that allows for adversarial-style attacks. We provide both the general proof formally alongside existential proofs of such intriguing LP-parameterizations based on SCM for three combinatorial problems, namely Linear Assignment, Shortest Path and a real world problem of energy systems.<\/jats:p>","DOI":"10.1007\/s10994-023-06431-9","type":"journal-article","created":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T17:03:03Z","timestamp":1704819783000},"page":"1329-1349","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Structural causal models reveal confounder bias in linear program modelling"],"prefix":"10.1007","volume":"113","author":[{"given":"Matej","family":"Ze\u010devi\u0107","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4331-7193","authenticated-orcid":false,"given":"Devendra Singh","family":"Dhami","sequence":"additional","affiliation":[]},{"given":"Kristian","family":"Kersting","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,9]]},"reference":[{"key":"6431_CR1","unstructured":"Abernethy, J., Lee, C., Sinha, A., & Tewari, A. (2014). Online linear optimization via smoothing. In Conference on learning theory (pp. 807\u2013823). PMLR."},{"key":"6431_CR2","first-page":"9562","volume":"32","author":"A Agrawal","year":"2019","unstructured":"Agrawal, A., Amos, B., Barratt, S., Boyd, S., Diamond, S., & Kolter, Z. (2019). Differentiable convex optimization layers. Neural Information Processing Systems, 32, 9562\u20139574.","journal-title":"Neural Information Processing Systems"},{"key":"6431_CR3","unstructured":"Amos, B., & Kolter, J. Z. (2017). OptNet: Differentiable optimization as a layer in neural networks. In International conference on machine learning (pp. 136\u2013145). PMLR."},{"issue":"2\u20133","key":"6431_CR4","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1561\/2200000039","volume":"6","author":"F Bach","year":"2013","unstructured":"Bach, F. (2013). Learning with submodular functions: A convex optimization perspective. Foundations and Trends in Machine Learning, 6(2\u20133), 145\u2013373.","journal-title":"Foundations and Trends in Machine Learning"},{"key":"6431_CR5","first-page":"9508","volume":"33","author":"Q Berthet","year":"2020","unstructured":"Berthet, Q., Blondel, M., Teboul, O., Cuturi, M., Vert, J.-P., & Bach, F. (2020). Learning with differentiable perturbed optimizers. Neural Information Processing Systems, 33, 9508\u20139519.","journal-title":"Neural Information Processing Systems"},{"key":"6431_CR6","unstructured":"Bica, I., Alaa, A., & Van Der Schaar, M. (2020). Time series deconfounder: Estimating treatment effects over time in the presence of hidden confounders. In International conference on machine learning (pp. 884\u2013895). PMLR."},{"key":"6431_CR7","unstructured":"Brendel, W., Rauber, J., & Bethge, M. (2018). Decision-based adversarial attacks: Reliable attacks against black-box machine learning models, In International conference on learning representations. https:\/\/openreview.net\/forum?id=SyZI0GWCZ"},{"key":"6431_CR8","doi-asserted-by":"crossref","unstructured":"Chen, S.-T., Cornelius, C., Martin, J., & Chau, D. H. P. (2018). Shapeshifter: Robust physical adversarial attack on faster R-CNN object detector. In Machine learning and knowledge discovery in databases: European conference, ECML PKDD 2018, Dublin, Ireland, September 10\u201314, 2018, Proceedings, Part I 18 (pp. 52\u201368). Springer International Publishing.","DOI":"10.1007\/978-3-030-10925-7_4"},{"key":"6431_CR9","unstructured":"Eghbal-zadeh, H., Koutini, K., Primus, P., Haunschmid, V., Lewandowski, M., Zellinger, W., Moser, B. A., & Widmer, G. (2020). On data augmentation and adversarial risk: An empirical analysis. arxiv preprint arxiv:2007.02650"},{"key":"6431_CR10","unstructured":"Goodfellow, I. J., Shlens, J., & Szegedy, C. (2015). Explaining and harnessing adversarial examples. In International conference on learning representations. arxiv.org\/abs\/1412.6572"},{"key":"6431_CR11","unstructured":"Gumbel, E. J. (1954). Statistical theory of extreme values and some practical applications: A series of lectures (Vol. 33). US Government Printing Office."},{"key":"6431_CR12","unstructured":"Guo, C., Gardner, J., You, Y., Wilson, A. G., & Weinberger, K. (2019). Simple black-box adversarial attacks. In International conference on machine learning (pp. 2484\u20132493). PMLR."},{"issue":"1","key":"6431_CR13","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1080\/10696679.2020.1860683","volume":"29","author":"JF Hair Jr","year":"2021","unstructured":"Hair, J. F., Jr., & Sarstedt, M. (2021). Data, measurement, and causal inferences in machine learning: Opportunities and challenges for marketing. Journal of Marketing Theory and Practice, 29(1), 65\u201377.","journal-title":"Journal of Marketing Theory and Practice"},{"issue":"2","key":"6431_CR14","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1002\/j.1538-7305.1950.tb00463.x","volume":"29","author":"RW Hamming","year":"1950","unstructured":"Hamming, R. W. (1950). Error detecting and error correcting codes. The Bell System Technical Booktitle, 29(2), 147\u2013160.","journal-title":"The Bell System Technical Booktitle"},{"key":"6431_CR15","doi-asserted-by":"crossref","unstructured":"Handa, A., Sharma, A., & Shukla, S. K. (2019). Machine learning in cybersecurity: A review. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery.","DOI":"10.1002\/widm.1306"},{"key":"6431_CR16","unstructured":"Hern\u00e1n, M. A., & Robins, J. M. (2020). Causal inference: What if. Chapman & Hall\/CRC."},{"key":"6431_CR17","unstructured":"Hoiles, W., & Schaar, M. (2016). Bounded off-policy evaluation with missing data for course recommendation and curriculum design. In International conference on machine learning (pp. 1596\u20131604). PMLR."},{"key":"6431_CR18","unstructured":"Ilse, M., Tomczak, J. M., & Forr\u00e9, P. (2021). Selecting data augmentation for simulating interventions. In International conference on machine learning (pp. 4555\u20134562). PMLR."},{"key":"6431_CR19","unstructured":"Loulou, R., Remme, U., Kanudia, A., Lehtila, A., & Goldstein, G. (2005). Documentation for the times model part II. Energy technology systems analysis programme. International Energy Agency."},{"key":"6431_CR20","first-page":"7272","volume":"33","author":"J Mandi","year":"2020","unstructured":"Mandi, J., & Guns, T. (2020). Interior point solving for LP-based prediction+ optimisation. Neural Information Processing Systems, 33, 7272\u20137282.","journal-title":"Neural Information Processing Systems"},{"key":"6431_CR21","doi-asserted-by":"crossref","unstructured":"Papandreou, G., & Yuille, A. L. (2011). Perturb-and-map random fields: Using discrete optimization to learn and sample from energy models. In 2011 international conference on computer vision (pp. 193\u2013200). IEEE.","DOI":"10.1109\/ICCV.2011.6126242"},{"key":"6431_CR22","unstructured":"Paulus, A., Rol\u00ednek, M., Musil, V., Amos, B., & Martius, G. (2021). CombOptNet: Fit the right NP-hard problem by learning integer programming constraints. arxiv preprint arxiv:2105.02343"},{"key":"6431_CR23","doi-asserted-by":"crossref","unstructured":"Pearl, J. (2009). Causality. Cambridge University Press.","DOI":"10.1017\/CBO9780511803161"},{"key":"6431_CR24","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1146\/annurev.psych.58.110405.085555","volume":"58","author":"DC Penn","year":"2007","unstructured":"Penn, D. C., & Povinelli, D. J. (2007). Causal cognition in human and nonhuman animals: A comparative, critical review. Annual Review of Psychology, 58, 97\u2013118.","journal-title":"Annual Review of Psychology"},{"key":"6431_CR25","unstructured":"Peters, J., Janzing, D., & Sch\u00f6lkopf, B. (2017). Elements of causal inference. MIT Press."},{"key":"6431_CR26","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.enpol.2011.12.040","volume":"43","author":"K Schaber","year":"2012","unstructured":"Schaber, K., Steinke, F., & Hamacher, T. (2012). Transmission grid extensions for the integration of variable renewable energies in Europe: Who benefits where? Energy Policy, 43, 123\u2013135.","journal-title":"Energy Policy"},{"key":"6431_CR27","first-page":"1643","volume":"11","author":"P Spirtes","year":"2010","unstructured":"Spirtes, P. (2010). Introduction to causal inference. Journal of Machine Learning Research, 11, 1643\u20131662.","journal-title":"Journal of Machine Learning Research"},{"key":"6431_CR28","unstructured":"Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2014). Intriguing properties of neural networks. In International conference on learning representations. arxiv.org\/abs\/1312.6199"},{"key":"6431_CR29","unstructured":"Tjeng, V., Xiao, K. Y., & Tedrake, R. (2019). Evaluating robustness of neural networks with mixed integer programming. In International conference on learning representations. https:\/\/openreview.net\/forum?id=HyGIdiRqtm"},{"key":"6431_CR30","unstructured":"Wu, K., Wang, A., & Yu, Y. (2020). Stronger and faster wasserstein adversarial attacks. In International conference on machine learning (pp. 10377\u201310387). PMLR."},{"key":"6431_CR31","doi-asserted-by":"crossref","unstructured":"Zhou, N., Luo, W., Lin, X., Xu, P., & Zhang, Z. (2020). Generating multi-label adversarial examples by linear programming. In 2020 international joint conference on neural networks (IJCNN) (pp. 1\u20138). IEEE.","DOI":"10.1109\/IJCNN48605.2020.9206614"},{"key":"6431_CR32","doi-asserted-by":"crossref","unstructured":"Z\u00fcgner, D., Akbarnejad, A., & G\u00fcnnemann, S. (2018). Adversarial attacks on neural networks for graph data. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining (pp. 2847\u20132856).","DOI":"10.1145\/3219819.3220078"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06431-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-023-06431-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06431-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T23:05:03Z","timestamp":1708988703000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-023-06431-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,9]]},"references-count":32,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["6431"],"URL":"https:\/\/doi.org\/10.1007\/s10994-023-06431-9","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2024,1,9]]},"assertion":[{"value":"10 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 August 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 October 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 January 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no competing interests to declare.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Ethics approval was not required for this research.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}]}}