{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T01:17:03Z","timestamp":1775870223488,"version":"3.50.1"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197741","type":"print"},{"value":"9783031197758","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19775-8_24","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T12:12:59Z","timestamp":1666440779000},"page":"404-421","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":49,"title":["Are Vision Transformers Robust to\u00a0Patch Perturbations?"],"prefix":"10.1007","author":[{"given":"Jindong","family":"Gu","sequence":"first","affiliation":[]},{"given":"Volker","family":"Tresp","sequence":"additional","affiliation":[]},{"given":"Yao","family":"Qin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Abnar, S., Zuidema, W.: Quantifying attention flow in transformers. In: Annual Meeting of the Association for Computational Linguistics (ACL) (2020)","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"24_CR2","unstructured":"Aldahdooh, A., Hamidouche, W., Deforges, O.: Reveal of vision transformers robustness against adversarial attacks. arXiv:2106.03734 (2021)"},{"key":"24_CR3","unstructured":"Bai, Y., Mei, J., Yuille, A., Xie, C.: Are transformers more robust than CNNs? arXiv:2111.05464 (2021)"},{"key":"24_CR4","unstructured":"Benz, P., Ham, S., Zhang, C., Karjauv, A., Kweon, I.S.: Adversarial robustness comparison of vision transformer and MLP-mixer to CNNs. arXiv preprint arXiv:2110.02797 (2021)"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Bhojanapalli, S., Chakrabarti, A., Glasner, D., Li, D., Unterthiner, T., Veit, A.: Understanding robustness of transformers for image classification. arXiv:2103.14586 (2021)","DOI":"10.1109\/ICCV48922.2021.01007"},{"key":"24_CR6","unstructured":"Brown, T.B., Man\u00e9, D., Roy, A., Abadi, M., Gilmer, J.: Adversarial patch. arXiv:1712.09665v1 (2017)"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Chen, C.F., Fan, Q., Panda, R.: CrossVit: cross-attention multi-scale vision transformer for image classification. arXiv:2103.14899 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Z., Xie, L., Niu, J., Liu, X., Wei, L., Tian, Q.: VisFormer: the vision-friendly transformer. arXiv:2104.12533 (2021)","DOI":"10.1109\/ICCV48922.2021.00063"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"24_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv:2010.11929 (2020)"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Fawzi, A., Frossard, P.: Measuring the effect of nuisance variables on classifiers. In: Proceedings of the British Machine Vision Conference (BMVC) (2016)","DOI":"10.5244\/C.30.137"},{"key":"24_CR12","unstructured":"Fu, Y., Zhang, S., Wu, S., Wan, C., Lin, Y.: Patch-fool: are vision transformers always robust against adversarial perturbations? In: International Conference on Learning Representations (2021)"},{"key":"24_CR13","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv:1412.6572 (2014)"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Graham, B., et al.: Levit: a vision transformer in convnet\u2019s clothing for faster inference. arXiv:2104.01136 (2021)","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"24_CR15","unstructured":"Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., Wang, Y.: Transformer in transformer. arXiv:2103.00112 (2021)"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"24_CR17","unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"24_CR18","doi-asserted-by":"publisher","first-page":"1923","DOI":"10.1109\/LSP.2021.3112099","volume":"28","author":"H Hu","year":"2021","unstructured":"Hu, H., Lu, X., Zhang, X., Zhang, T., Sun, G.: Inheritance attention matrix-based universal adversarial perturbations on vision transformers. IEEE Sig. Process. Lett. 28, 1923\u20131927 (2021)","journal-title":"IEEE Sig. Process. Lett."},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"24_CR20","unstructured":"Joshi, A., Jagatap, G., Hegde, C.: Adversarial token attacks on vision transformers. arXiv:2110.04337 (2021)"},{"key":"24_CR21","unstructured":"Karmon, D., Zoran, D., Goldberg, Y.: Lavan: localized and visible adversarial noise. In: International Conference on Machine Learning (ICML) (2018)"},{"key":"24_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1007\/978-3-030-58558-7_29","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Kolesnikov","year":"2020","unstructured":"Kolesnikov, A., et al.: Big transfer (BiT): general visual representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 491\u2013507. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_29"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Liu, A., et al.: Perceptual-sensitive GAN for generating adversarial patches. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33011028"},{"key":"24_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/978-3-030-58601-0_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Liu","year":"2020","unstructured":"Liu, A., Wang, J., Liu, X., Cao, B., Zhang, C., Yu, H.: Bias-based universal adversarial patch attack for automatic check-out. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 395\u2013410. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_24"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Luo, J., Bai, T., Zhao, J.: Generating adversarial yet inconspicuous patches with a single image (student abstract). In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 15837\u201315838 (2021)","DOI":"10.1609\/aaai.v35i18.17915"},{"key":"24_CR27","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: arXiv:1706.06083 (2017)"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Mahmood, K., Mahmood, R., Van Dijk, M.: On the robustness of vision transformers to adversarial examples. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7838\u20137847 (2021)","DOI":"10.1109\/ICCV48922.2021.00774"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Mao, X., et al.: Towards robust vision transformer. arXiv:2105.07926 (2021)","DOI":"10.1109\/CVPR52688.2022.01173"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Mao, X., Qi, G., Chen, Y., Li, X., Ye, S., He, Y., Xue, H.: Rethinking the design principles of robust vision transformer. arXiv:2105.07926 (2021)","DOI":"10.1109\/CVPR52688.2022.01173"},{"key":"24_CR31","unstructured":"Metzen, J.H., Finnie, N., Hutmacher, R.: Meta adversarial training against universal patches. arXiv preprint arXiv:2101.11453 (2021)"},{"key":"24_CR32","unstructured":"Mu, N., Wagner, D.: Defending against adversarial patches with robust self-attention. In: ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning (2021)"},{"key":"24_CR33","unstructured":"Naseer, M., Ranasinghe, K., Khan, S., Hayat, M., Khan, F.S., Yang, M.H.: Intriguing properties of vision transformers. arXiv:2105.10497 (2021)"},{"key":"24_CR34","unstructured":"Naseer, M., Ranasinghe, K., Khan, S., Khan, F.S., Porikli, F.: On improving adversarial transferability of vision transformers. arXiv:2106.04169 (2021)"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z.B., Swami, A.: The limitations of deep learning in adversarial settings. In: 2016 IEEE European Symposium on Security and Privacy (EuroS &P) (2016)","DOI":"10.1109\/EuroSP.2016.36"},{"key":"24_CR36","unstructured":"Paul, S., Chen, P.Y.: Vision transformers are robust learners. arXiv:2105.07581 (2021)"},{"key":"24_CR37","unstructured":"Qian, Y., Wang, J., Wang, B., Zeng, S., Gu, Z., Ji, S., Swaileh, W.: Visually imperceptible adversarial patch attacks on digital images. arXiv preprint arXiv:2012.00909 (2020)"},{"key":"24_CR38","unstructured":"Qin, Y., Zhang, C., Chen, T., Lakshminarayanan, B., Beutel, A., Wang, X.: Understanding and improving robustness of vision transformers through patch-based negative augmentation. arXiv preprint arXiv:2110.07858 (2021)"},{"key":"24_CR39","doi-asserted-by":"crossref","unstructured":"Salman, H., Jain, S., Wong, E., Madry, A.: Certified patch robustness via smoothed vision transformers. arXiv:2110.07719 (2021)","DOI":"10.1109\/CVPR52688.2022.01471"},{"key":"24_CR40","doi-asserted-by":"crossref","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. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"24_CR41","unstructured":"Shao, R., Shi, Z., Yi, J., Chen, P.Y., Hsieh, C.J.: On the adversarial robustness of visual transformers. arXiv:2103.15670 (2021)"},{"key":"24_CR42","unstructured":"Shi, Y., Han, Y.: Decision-based black-box attack against vision transformers via patch-wise adversarial removal. arXiv preprint arXiv:2112.03492 (2021)"},{"key":"24_CR43","unstructured":"Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences. In: International Conference on Machine Learning (ICML) (2017)"},{"key":"24_CR44","unstructured":"Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., Fergus, R.: Intriguing properties of neural networks. In: International Conference on Learning Representations (ICLR) (2014)"},{"key":"24_CR45","unstructured":"Tang, S., et al.: Robustart: benchmarking robustness on architecture design and training techniques. arXiv preprint arXiv:2109.05211 (2021)"},{"key":"24_CR46","unstructured":"Tolstikhin, I., et al.: MLP-mixer: an all-MLP architecture for vision. In: arXiv:2105.01601 (2021)"},{"key":"24_CR47","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 (ICML) (2021)"},{"key":"24_CR48","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1109\/TIP.2021.3127849","volume":"31","author":"J Wang","year":"2021","unstructured":"Wang, J., Liu, A., Bai, X., Liu, X.: Universal adversarial patch attack for automatic checkout using perceptual and attentional bias. IEEE Trans. Image Process. 31, 598\u2013611 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"24_CR49","unstructured":"Wu, B., et al.: Visual transformers: token-based image representation and processing for computer vision. arXiv:2006.03677 (2020)"},{"key":"24_CR50","unstructured":"Xiao, T., Singh, M., Mintun, E., Darrell, T., Doll\u00e1r, P., Girshick, R.: Early convolutions help transformers see better. arXiv:2106.14881 (2021)"},{"key":"24_CR51","doi-asserted-by":"crossref","unstructured":"Yu, Z., Fu, Y., Li, S., Li, C., Lin, Y.: Mia-former: efficient and robust vision transformers via multi-grained input-adaptation. arXiv preprint arXiv:2112.11542 (2021)","DOI":"10.1609\/aaai.v36i8.20879"},{"key":"24_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818\u2013833. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53"},{"key":"24_CR53","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19775-8_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T13:44:12Z","timestamp":1710337452000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19775-8_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197741","9783031197758"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19775-8_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}