{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T03:44:44Z","timestamp":1787370284238,"version":"build-2736575974"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T00:00:00Z","timestamp":1776988800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Forschung Technologie und Raumfahrt Informationstechnikzentrum Bund","doi-asserted-by":"publisher","award":["01IS18037A"],"award-info":[{"award-number":["01IS18037A"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004349","name":"BASF SE","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004349","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006764","name":"Technische Universit\u00e4t Berlin","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006764","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","award":["RS-2022-II220984"],"award-info":[{"award-number":["RS-2022-II220984"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.inffus.2026.104406","type":"journal-article","created":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:10:50Z","timestamp":1777129850000},"page":"104406","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["Mitigating Clever Hans strategies in image classifiers through generating counterexamples"],"prefix":"10.1016","volume":"135","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1727-8577","authenticated-orcid":false,"given":"Sidney","family":"Bender","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1973-1909","authenticated-orcid":false,"given":"Ole","family":"Delzer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7209-0848","authenticated-orcid":false,"given":"Jan","family":"Herrmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5390-0633","authenticated-orcid":false,"given":"Heike Antje","family":"Marxfeld","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3861-7685","authenticated-orcid":false,"given":"Klaus-Robert","family":"M\u00fcller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7243-6186","authenticated-orcid":false,"given":"Gr\u00e9goire","family":"Montavon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104406_bib0001","series-title":"Clever Hans: (the horse of Mr. Von Osten.) A Contribution to Experimental Animal and Human Psychology","author":"Pfungst","year":"1911"},{"issue":"1","key":"10.1016\/j.inffus.2026.104406_bib0002","doi-asserted-by":"crossref","first-page":"1096","DOI":"10.1038\/s41467-019-08987-4","article-title":"Unmasking Clever Hans predictors and assessing what machines really learn","volume":"10","author":"Lapuschkin","year":"2019","journal-title":"Nat. Commun."},{"key":"10.1016\/j.inffus.2026.104406_bib0003","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1038\/s42256-025-01000-2","article-title":"Explainable AI reveals Clever Hans effects in unsupervised learning models","volume":"7","author":"Kauffmann","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104406_bib0004","unstructured":"O.f. E. Co-operation, Development, Recommendation of the council on artificial intelligence, 2024. Originally adopted in 2019, amended in 2024, https:\/\/legalinstruments.oecd.org\/en\/instruments\/OECD-LEGAL-0449."},{"key":"10.1016\/j.inffus.2026.104406_bib0005","doi-asserted-by":"crossref","unstructured":"J. K\u00f6men, E.D. de Jong, J. Hense, H. Marienwald, J. Dippel, P. Naumann, E. Marcus, L. Ruff, M. Alber, J. Teuwen, et al., Towards robust foundation models for digital pathology, arXiv: 2507.17845(2025).","DOI":"10.1038\/s41467-026-73923-2"},{"key":"10.1016\/j.inffus.2026.104406_bib0006","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Mixup: beyond empirical risk minimization","author":"Zhang","year":"2018"},{"key":"10.1016\/j.inffus.2026.104406_bib0007","series-title":"ICLR","article-title":"Effective data augmentation with diffusion models","author":"Trabucco","year":"2024"},{"key":"10.1016\/j.inffus.2026.104406_bib0008","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Distributionally robust neural networks","author":"Sagawa","year":"2020"},{"key":"10.1016\/j.inffus.2026.104406_bib0009","series-title":"International Conference on Machine Learning","first-page":"6781","article-title":"Just train twice: improving group robustness without training group information","author":"Liu","year":"2021"},{"key":"10.1016\/j.inffus.2026.104406_bib0010","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Last layer re-training is sufficient for robustness to spurious correlations","author":"Kirichenko","year":"2023"},{"issue":"3","key":"10.1016\/j.inffus.2026.104406_bib0011","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1109\/JPROC.2021.3060483","article-title":"Explaining deep neural networks and beyond: a review of methods and applications","volume":"109","author":"Samek","year":"2021","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.inffus.2026.104406_bib0012","article-title":"Getting aligned on representational alignment","volume":"2025","author":"Sucholutsky","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"issue":"8089","key":"10.1016\/j.inffus.2026.104406_bib0013","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1038\/s41586-025-09631-6","article-title":"Aligning machine and human visual representations across abstraction levels","volume":"647","author":"Muttenthaler","year":"2025","journal-title":"Nature"},{"issue":"8","key":"10.1016\/j.inffus.2026.104406_bib0014","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1038\/s42256-020-0212-3","article-title":"Making deep neural networks right for the right scientific reasons by interacting with their explanations","volume":"2","author":"Schramowski","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104406_bib0015","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/j.inffus.2021.07.015","article-title":"Finding and removing Clever Hans: using explanation methods to debug and improve deep models","volume":"77","author":"Anders","year":"2022","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104406_bib0016","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"21046","article-title":"From hope to safety: unlearning biases of deep models via gradient penalization in latent space","volume":"38","author":"Dreyer","year":"2024"},{"key":"10.1016\/j.inffus.2026.104406_bib0017","series-title":"ICLR","article-title":"Navigating neural space: revisiting concept activation vectors to overcome directional divergence","author":"Pahde","year":"2025"},{"key":"10.1016\/j.inffus.2026.104406_bib0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102094","article-title":"Preemptively pruning Clever-Hans strategies in deep neural networks","volume":"103","author":"Linhardt","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104406_bib0019","series-title":"ICCV (Workshops)","first-page":"2599","article-title":"Towards fixing Clever-Hans predictors with counterfactual knowledge distillation","author":"Bender","year":"2023"},{"key":"10.1016\/j.inffus.2026.104406_bib0020","series-title":"ICLR Workshop","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017"},{"key":"10.1016\/j.inffus.2026.104406_bib0021","series-title":"IEEE International Conference on Computer Vision (ICCV)","first-page":"6023","article-title":"CutMix: regularization strategy to train strong classifiers with localizable features","author":"Yun","year":"2019"},{"key":"10.1016\/j.inffus.2026.104406_bib0022","series-title":"IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","first-page":"702","article-title":"RandAugment: practical automated data augmentation with a reduced search space","author":"Cubuk","year":"2020"},{"key":"10.1016\/j.inffus.2026.104406_bib0023","series-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"113","article-title":"AutoAugment: learning augmentation policies from data","author":"Cubuk","year":"2019"},{"key":"10.1016\/j.inffus.2026.104406_bib0024","series-title":"International Conference on Learning Representations (ICLR)","article-title":"AugMix: a simple data processing method to improve robustness and uncertainty","author":"Hendrycks","year":"2020"},{"key":"10.1016\/j.inffus.2026.104406_bib0025","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","first-page":"5334","article-title":"Generalizing to unseen domains via adversarial data augmentation","author":"Volpi","year":"2018"},{"key":"10.1016\/j.inffus.2026.104406_bib0026","series-title":"International Conference on Learning Representations (ICLR)","article-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","author":"Geirhos","year":"2019"},{"key":"10.1016\/j.inffus.2026.104406_bib0027","series-title":"Proceedings of the 2019 AAAI\/ACM Conference on AI, Ethics, and Society","first-page":"239","article-title":"Explanatory interactive machine learning","author":"Teso","year":"2019"},{"key":"10.1016\/j.inffus.2026.104406_bib0028","series-title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","article-title":"Right for the right reasons: training differentiable models by constraining their explanations","author":"Ross","year":"2017"},{"key":"10.1016\/j.inffus.2026.104406_bib0029","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3532","article-title":"Reactive model correction: mitigating harm to task-relevant features via conditional bias suppression","author":"Bareeva","year":"2024"},{"key":"10.1016\/j.inffus.2026.104406_bib0030","series-title":"ICLR","article-title":"Learning the difference that makes a difference with counterfactually-augmented data","author":"Kaushik","year":"2020"},{"key":"10.1016\/j.inffus.2026.104406_bib0031","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"11362","article-title":"Counterfactual active learning for out-of-distribution generalization","author":"Deng","year":"2023"},{"key":"10.1016\/j.inffus.2026.104406_bib0032","series-title":"EMNLP","article-title":"Improving classifier robustness through active generation of pairwise counterfactuals","author":"Balashankar","year":"2023"},{"key":"10.1016\/j.inffus.2026.104406_bib0033","series-title":"EMNLP","article-title":"Active learning by acquiring contrastive examples","author":"Margatina","year":"2021"},{"issue":"5","key":"10.1016\/j.inffus.2026.104406_bib0034","doi-asserted-by":"crossref","first-page":"3257","DOI":"10.1109\/TPAMI.2023.3339980","article-title":"Diffeomorphic counterfactuals with generative models","volume":"46","author":"Dombrowski","year":"2024","journal-title":"IEEE Trans. Pattern Recognit. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104406_bib0035","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"1056","article-title":"Beyond trivial counterfactual explanations with diverse valuable explanations","author":"Rodriguez","year":"2021"},{"key":"10.1016\/j.inffus.2026.104406_bib0036","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16425","article-title":"Adversarial counterfactual visual explanations","author":"Jeanneret","year":"2023"},{"key":"10.1016\/j.inffus.2026.104406_bib0037","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104406_bib0038","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11461","article-title":"Repaint: inpainting using denoising diffusion probabilistic models","author":"Lugmayr","year":"2022"},{"key":"10.1016\/j.inffus.2026.104406_bib0039","doi-asserted-by":"crossref","first-page":"364","DOI":"10.52202\/068431-0027","article-title":"Diffusion visual counterfactual explanations","volume":"35","author":"Augustin","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104406_bib0040","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11093","article-title":"DiG-IN: diffusion guidance for investigating networks-uncovering classifier differences neuron visualisations and visual counterfactual explanations","author":"Augustin","year":"2024"},{"key":"10.1016\/j.inffus.2026.104406_bib0041","series-title":"Proceedings of the Asian Conference on Computer Vision","first-page":"858","article-title":"Diffusion models for counterfactual explanations","author":"Jeanneret","year":"2022"},{"key":"10.1016\/j.inffus.2026.104406_bib0042","series-title":"European Conference on Computer Vision","first-page":"338","article-title":"Fast diffusion-based counterfactuals for shortcut removal and generation","author":"Weng","year":"2025"},{"key":"10.1016\/j.inffus.2026.104406_bib0043","series-title":"Advances in Neural Information Processing Systems 34 (NeurIPS)","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","author":"Dhariwal","year":"2021"},{"key":"10.1016\/j.inffus.2026.104406_bib0044","series-title":"3rd Annual Conference for Explainable Machine Learning","article-title":"Diffusion counterfactuals for image regressors","author":"Ha","year":"2025"},{"key":"10.1016\/j.inffus.2026.104406_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112811","article-title":"Towards desiderata-driven design of visual counterfactual explainers","volume":"174","author":"Bender","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.inffus.2026.104406_bib0046","series-title":"International Conference On Learning Representations 2024","article-title":"On the foundations of shortcut learning","author":"Hermann","year":"2023"},{"key":"10.1016\/j.inffus.2026.104406_bib0047","series-title":"Proceedings of International Conference on Computer Vision (ICCV)","article-title":"Deep learning face attributes in the wild","author":"Liu","year":"2015"},{"key":"10.1016\/j.inffus.2026.104406_bib0048","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16036","article-title":"Nico++: towards better benchmarking for domain generalization","author":"Zhang","year":"2023"},{"key":"10.1016\/j.inffus.2026.104406_bib0049","unstructured":"L. Gall\u00e9e, Y. Xiong, M. Beer, M. G\u00f6tz, FunnyNodules: a customizable medical dataset tailored for evaluating explainable AI, arXiv: 2511.15481(2025)."},{"issue":"2","key":"10.1016\/j.inffus.2026.104406_bib0050","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1109\/TMI.2018.2867350","article-title":"From detection of individual metastases to classification of lymph node status at the patient level: the camelyon17 challenge","volume":"38","author":"Bandi","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.inffus.2026.104406_bib0051","doi-asserted-by":"crossref","unstructured":"O.f. E. Co-operation, Development, Test No. 443: extended one-generation reproductive toxicity study, OECD guidelines for the testing of chemicals, Section 4, OECD Publishing, Paris, 2025. https:\/\/doi.org\/10.1787\/9789264185371-en.","DOI":"10.1787\/9789264185371-en"},{"issue":"3","key":"10.1016\/j.inffus.2026.104406_bib0052","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1038\/s41591-024-02857-3","article-title":"Towards a general-purpose foundation model for computational pathology","volume":"30","author":"Chen","year":"2024","journal-title":"Nat. Med."},{"issue":"4","key":"10.1016\/j.inffus.2026.104406_bib0053","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2026.104406_bib0054","unstructured":"S. Bender, M. Morik, Visual disentangled diffusion autoencoders: scalable counterfactual generation for foundation models, CoRR abs\/2601.21851(2026)."},{"key":"10.1016\/j.inffus.2026.104406_bib0055","unstructured":"T. Spooner, D. Dervovic, J. Long, J. Shepard, J. Chen, D. Magazzeni, Counterfactual explanations for arbitrary regression models, CoRR abs\/2106.15212(2021)."}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S156625352600285X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S156625352600285X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T08:31:34Z","timestamp":1783067494000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S156625352600285X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":55,"alternative-id":["S156625352600285X"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104406","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Mitigating Clever Hans strategies in image classifiers through generating counterexamples","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104406","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104406"}}