{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T16:29:17Z","timestamp":1787070557322,"version":"3.56.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032083265","type":"print"},{"value":"9783032083272","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Machine learning models tend to learn spurious features \u2013 features that strongly correlate with target labels but are not causal. Existing approaches to mitigate models\u2019 dependence on spurious features work in some cases, but fail in others. In this paper, we systematically analyze how and where neural networks encode spurious correlations. We introduce the neuron spurious score, an XAI-based diagnostic measure to quantify a neuron\u2019s dependence on spurious features. We analyze both convolutional neural networks (CNNs) and vision transformers (ViTs) using architecture-specific methods. Our results show that spurious features are partially disentangled, but the degree of disentanglement varies across model architectures. Furthermore, we find that the assumptions behind existing mitigation methods are incomplete. Our results lay the groundwork for the development of novel methods to mitigate spurious correlations and make AI models safer to use in practice.<\/jats:p>","DOI":"10.1007\/978-3-032-08327-2_20","type":"book-chapter","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T18:07:07Z","timestamp":1760206027000},"page":"424-445","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An XAI-Based Analysis of\u00a0Shortcut Learning in\u00a0Neural Networks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7658-0599","authenticated-orcid":false,"given":"Phuong Quynh","family":"Le","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3678-0390","authenticated-orcid":false,"given":"J\u00f6rg","family":"Schl\u00f6tterer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6776-3868","authenticated-orcid":false,"given":"Christin","family":"Seifert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"key":"20_CR1","unstructured":"Arjovsky, M., Bottou, L., Gulrajani, I., Lopez-Paz, D.: Invariant risk minimization. arXiv preprint arXiv:1907.02893 (2019)"},{"key":"20_CR2","unstructured":"Bao, Y., Chang, S., Barzilay, R.: Predict then interpolate: a simple algorithm to learn stable classifiers. In: International Conference on Machine Learning, pp. 640\u2013650. PMLR (2021)"},{"key":"20_CR3","unstructured":"Codella, N., et al.: Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the international skin imaging collaboration (ISIC) (2019)"},{"key":"20_CR4","unstructured":"Creager, E., Jacobsen, J.H., Zemel, R.: Environment inference for invariant learning. In: International Conference on Machine Learning, pp. 2189\u20132200. PMLR (2021)"},{"key":"20_CR5","unstructured":"Csord\u00e1s, R., van Steenkiste, S., Schmidhuber, J.: Are neural nets modular? Inspecting functional modularity through differentiable weight masks. In: International Conference on Learning Representations (2020)"},{"key":"20_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale, June 2021, arXiv:2010.11929 [cs]"},{"issue":"11","key":"20_CR7","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1038\/s42256-020-00257-z","volume":"2","author":"R Geirhos","year":"2020","unstructured":"Geirhos, R., et al.: Shortcut learning in deep neural networks. Nat. Mach. Intell. 2(11), 665\u2013673 (2020)","journal-title":"Nat. Mach. Intell."},{"key":"20_CR8","unstructured":"Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness. In: International Conference on Learning Representations (2018)"},{"key":"20_CR9","unstructured":"Hakemi, S., Akhtar, N., Hassan, G.M., Mian, A.: Post-hoc spurious correlation neutralization with single-weight fictitious class unlearning, January 2025"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"20_CR11","unstructured":"Kirichenko, P., Izmailov, P., Wilson, A.G.: last layer re-training is sufficient for robustness to spurious correlations. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"20_CR12","unstructured":"Le, P.Q., Schl\u00f6tterer, J., Seifert, C.: Is last layer re-training truly sufficient for robustness to spurious correlations? arXiv preprint arXiv:2308.00473 (2023)"},{"key":"20_CR13","unstructured":"Le, P.Q., Schl\u00f6tterer, J., Seifert, C.: Out of spuriousity: improving robustness to spurious correlations without group annotations. arXiv preprint arXiv:2407.14974 (2024)"},{"key":"20_CR14","doi-asserted-by":"publisher","first-page":"59239","DOI":"10.52202\/075280-2586","volume":"36","author":"Z Lin","year":"2023","unstructured":"Lin, Z., Gao, Y., Yang, Y., Sang, J.: Revisiting visual model robustness: a frequency long-tailed distribution view. Adv. Neural. Inf. Process. Syst. 36, 59239\u201359251 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR15","unstructured":"Liu, E.Z., et al.: Just train twice: improving group robustness without training group information. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 6781\u20136792. PMLR, July 2021, https:\/\/proceedings.mlr.press\/v139\/liu21f.html"},{"key":"20_CR16","unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9(11) (2008)"},{"key":"20_CR17","unstructured":"Nam, J., Cha, H., Ahn, S., Lee, J., Shin, J.: Learning from failure: de-biasing classifier from biased classifier. Adv. Neural Inf. Process. Syst. 33, 20673\u201320684 (2020), https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/eddc3427c5d77843c2253f1e799fe933-Paper.pdf"},{"key":"20_CR18","unstructured":"Nam, J., Kim, J., Lee, J., Shin, J.: Spread spurious attribute: improving worst-group accuracy with spurious attribute estimation. In: 10th International Conference on Learning Representations, ICLR 2022 (2022)"},{"issue":"1","key":"20_CR19","doi-asserted-by":"publisher","first-page":"40","DOI":"10.3390\/diagnostics12010040","volume":"12","author":"M Nauta","year":"2021","unstructured":"Nauta, M., Walsh, R., Dubowski, A., Seifert, C.: Uncovering and correcting shortcut learning in machine learning models for skin cancer diagnosis. Diagnostics 12(1), 40 (2021). https:\/\/doi.org\/10.3390\/diagnostics12010040","journal-title":"Diagnostics"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Park, G.Y., Lee, S., Lee, S.W., Ye, J.C.: Training debiased subnetworks with contrastive weight pruning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7929\u20137938 (2023), https:\/\/openaccess.thecvf.com\/content\/CVPR2023\/papers\/Park_Training_Debiased_Subnetworks_With_Contrastive_Weight_Pruning_CVPR_2023_paper.pdf","DOI":"10.1109\/CVPR52729.2023.00766"},{"key":"20_CR21","unstructured":"Qiu, S., Potapczynski, A., Izmailov, P., Wilson, A.G.: Simple and fast group robustness by automatic feature reweighting. In: International Conference on Machine Learning, pp. 28448\u201328467. PMLR (2023)"},{"key":"20_CR22","unstructured":"Rieger, L., Singh, C., Murdoch, W.J., Yu, B.: Interpretations are useful: penalizing explanations to align neural networks with prior knowledge. In: Proceedings of the 37th International Conference on Machine Learning, p.\u00a011. JMLR.org (2020), http:\/\/proceedings.mlr.press\/v119\/rieger20a\/rieger20a.pdf"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. In: The Annals of Mathematical Statistics, pp. 400\u2013407 (1951)","DOI":"10.1214\/aoms\/1177729586"},{"key":"20_CR24","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"20_CR25","unstructured":"Sagawa, S., Koh, P.W., Hashimoto, T.B., Liang, P.: Distributionally robust neural networks. In: International Conference on Learning Representations (2020)"},{"key":"20_CR26","unstructured":"Sagawa, S., Raghunathan, A., Koh, P.W., Liang, P.: An investigation of why overparameterization exacerbates spurious correlations. In: III, H.D., Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0119, pp. 8346\u20138356. PMLR, July 2020, https:\/\/proceedings.mlr.press\/v119\/sagawa20a.html"},{"issue":"2","key":"20_CR27","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","volume":"128","author":"RR Selvaraju","year":"2019","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vision 128(2), 336\u2013359 (2019). https:\/\/doi.org\/10.1007\/s11263-019-01228-7","journal-title":"Int. J. Comput. Vision"},{"key":"20_CR28","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"20_CR29","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: Caltech-UCSD Birds 200. Technical Report, California Institute of Technology (2011)"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"20_CR31","unstructured":"Zhang, M., Sohoni, N.S., Zhang, H.R., Finn, C., Re, C.: Correct-N-contrast: a contrastive approach for improving robustness to spurious correlations. In: International Conference on Machine Learning, pp. 26484\u201326516. PMLR (2022), https:\/\/proceedings.mlr.press\/v162\/zhang22z\/zhang22z.pdf"},{"issue":"6","key":"20_CR32","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","volume":"40","author":"B Zhou","year":"2018","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1452\u20131464 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2723009","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Communications in Computer and Information Science","Explainable Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-08327-2_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T15:29:23Z","timestamp":1787066963000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-08327-2_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"ISBN":["9783032083265","9783032083272"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-08327-2_20","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"12 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"xAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"World Conference on Explainable Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Istanbul","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"T\u00fcrkiye","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"xai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/xaiworldconference.com\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}