{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:31:18Z","timestamp":1768854678307,"version":"3.49.0"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032144911","type":"print"},{"value":"9783032144928","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-14492-8_3","type":"book-chapter","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T07:07:53Z","timestamp":1768806473000},"page":"27-40","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["NeuroShield-ViT: Mechanistic Understandings of\u00a0Representation Vulnerabilities and\u00a0Engineering Robust Vision Transformers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4048-5784","authenticated-orcid":false,"given":"Chashi Mahiul","family":"Islam","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0948-4234","authenticated-orcid":false,"given":"Samuel Jacob","family":"Chacko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7114-6484","authenticated-orcid":false,"given":"Mao","family":"Nishino","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9320-3872","authenticated-orcid":false,"given":"Xiuwen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,20]]},"reference":[{"key":"3_CR1","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"3_CR2","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: Beit: BERT pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)"},{"key":"3_CR3","unstructured":"Baras, A., Zolfi, A., Elovici, Y., Shabtai, A.: Quantattack: exploiting dynamic quantization to attack vision transformers. arXiv preprint arXiv:2312.02220 (2023)"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer, Cham (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"3_CR5","doi-asserted-by":"publisher","unstructured":"Carlini, N., Wagner, D.: Adversarial examples are not easily detected: Bypassing ten detection methods. In: Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security, AISec 2017, pp. 3\u201314. Association for Computing Machinery, New York, NY, USA (2017). https:\/\/doi.org\/10.1145\/3128572.3140444","DOI":"10.1145\/3128572.3140444"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: 2017 IEEE Symposium on Security and Privacy (SP). IEEE (2017)","DOI":"10.1109\/SP.2017.49"},{"key":"3_CR7","unstructured":"Chacko, S.J., Biswas, S., Islam, C.M., Liza, F.T., Liu, X.: Adversarial attacks on large language models using regularized relaxation. arXiv preprint arXiv:2410.19160 (2024)"},{"key":"3_CR8","unstructured":"Cohen, J., Rosenfeld, E., Kolter, Z.: Certified adversarial robustness via randomized smoothing. In: international Conference on Machine Learning, pp. 1310\u20131320. PMLR (2019)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Dar, G., Geva, M., Gupta, A., Berant, J.: Analyzing transformers in embedding space. arXiv preprint arXiv:2209.02535 (2022)","DOI":"10.18653\/v1\/2023.acl-long.893"},{"key":"3_CR10","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: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3_CR11","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Dong, L., Xu, S., Xu, B.: Speech-transformer: a no-recurrence sequence-to-sequence model for speech recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5884\u20135888. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"3_CR13","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"3_CR14","unstructured":"Fu, Y., Zhang, S., Wu, S., Wan, C., Lin, Y.: Patch-fool: are vision transformers always robust against adversarial perturbations? arXiv preprint arXiv:2203.08392 (2022)"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Gong, H., Dong, M., Ma, S., Camtepe, S., Nepal, S., Xu, C.: Random entangled tokens for adversarially robust vision transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24554\u201324563 (2024)","DOI":"10.1109\/CVPR52733.2024.02318"},{"key":"3_CR16","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"3_CR18","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":"3_CR19","unstructured":"Howard, J.: imagenette (2019). https:\/\/github.com\/fastai\/imagenette\/"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Islam, C.M., Salman, S., Shams, M., Liu, X., Kumar, P.: Malicious path manipulations via exploitation of representation vulnerabilities of vision-language navigation systems. arXiv preprint arXiv:2407.07392 (2024)","DOI":"10.1109\/IROS58592.2024.10802618"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Kim, G., Kim, J., Lee, J.S.: Exploring adversarial robustness of vision transformers in the spectral perspective. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3976\u20133985 (2024)","DOI":"10.1109\/WACV57701.2024.00393"},{"key":"3_CR22","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)"},{"key":"3_CR23","unstructured":"Krizhevsky, A., Nair, V., Hinton, G.: Cifar-10 (canadian institute for advanced research). 5(4), 1 (2010). http:\/\/www.cs.toronto.edu\/kriz\/cifar.html"},{"key":"3_CR24","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25 (2012)"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Kurakin, A., Goodfellow, I.J., Bengio, S.: Adversarial examples in the physical world. In: Artificial Intelligence Safety and Security, pp. 99\u2013112. Chapman and Hall\/CRC (2018)","DOI":"10.1201\/9781351251389-8"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, C., Xu, C.: Harnessing edge information for improved robustness in vision transformers. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 3252\u20133260 (2024)","DOI":"10.1609\/aaai.v38i4.28110"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Li, Y., Xu, C.: Trade-off between robustness and accuracy of vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7558\u20137568 (2023)","DOI":"10.1109\/CVPR52729.2023.00730"},{"key":"3_CR28","unstructured":"Liu, L., Guo, Y., Zhang, Y., Yang, J.: Understanding and defending patched-based adversarial attacks for vision transformer. In: Proceedings of the 40th International Conference on Machine Learning, pp. 21631\u201321657 (2023)"},{"key":"3_CR29","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)"},{"key":"3_CR30","first-page":"18599","volume":"35","author":"Y Mo","year":"2022","unstructured":"Mo, Y., Wu, D., Wang, Y., Guo, Y., Wang, Y.: When adversarial training meets vision transformers: recipes from training to architecture. Adv. Neural. Inf. Process. Syst. 35, 18599\u201318611 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR31","unstructured":"Oquab, M., et\u00a0al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"3_CR32","unstructured":"Papernot, N., McDaniel, P., Goodfellow, I.J.: Transferability in machine learning: from phenomena to black-box attacks using adversarial samples. In: IEEE European Symposium on Security and Privacy (EuroS &P), pp. 123\u2013138. IEEE (2016)"},{"key":"3_CR33","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. PMLR (2021)"},{"key":"3_CR34","first-page":"12116","volume":"34","author":"M Raghu","year":"2021","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., Dosovitskiy, A.: Do vision transformers see like convolutional neural networks? Adv. Neural. Inf. Process. Syst. 34, 12116\u201312128 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR35","unstructured":"Rando, J., Naimi, N., Baumann, T., Mathys, M.: Exploring adversarial attacks and defenses in vision transformers trained with dino. arXiv preprint arXiv:2206.06761 (2022)"},{"key":"3_CR36","unstructured":"Salman, S., Shams, M.M.B., Liu, X.: Intriguing equivalence structures of the embedding space of vision transformers. arXiv preprint arXiv:2401.15568 (2024)"},{"key":"3_CR37","unstructured":"Shao, R., Shi, Z., Yi, J., Chen, P.Y., Hsieh, C.J.: On the adversarial robustness of vision transformers. arXiv preprint arXiv:2103.15670 (2021)"},{"key":"3_CR38","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":"3_CR39","unstructured":"Turner, A., Thiergart, L., Udell, D., Leech, G., Mini, U., MacDiarmid, M.: Activation addition: steering language models without optimization. arXiv preprint arXiv:2308.10248 (2023)"},{"key":"3_CR40","unstructured":"Vaswani, A.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)"},{"key":"3_CR41","unstructured":"Vilas, M.G., Schauml\u00f6ffel, T., Roig, G.: Analyzing vision transformers for image classification in class embedding space. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"3_CR42","doi-asserted-by":"crossref","unstructured":"Wallace, E., Feng, S., Kandpal, N., Gardner, M., Singh, S.: Universal adversarial triggers for attacking and analyzing NLP. arXiv preprint arXiv:1908.07125 (2019)","DOI":"10.18653\/v1\/D19-1221"},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Wang, F., Shao, M., Meng, L., Liu, F.: Dual stage black-box adversarial attack against vision transformer. Int. J. Mach. Learn. Cybern. 1\u201312 (2024)","DOI":"10.1007\/s13042-024-02097-4"},{"key":"3_CR44","unstructured":"Wang, Y., Zou, D., Yi, J., Bailey, J., Ma, X., Gu, Q.: Improving adversarial robustness requires revisiting misclassified examples. In: International Conference on Learning Representations (2019)"},{"key":"3_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Z., Ruan, W.: Understanding adversarial robustness of vision transformers via cauchy problem. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 562\u2013577. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-26409-2_34"},{"key":"3_CR46","unstructured":"Wei, B., et al.: Assessing the brittleness of safety alignment via pruning and low-rank modifications. arXiv preprint arXiv:2402.05162 (2024)"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Wei, Z., Chen, J., Goldblum, M., Wu, Z., Goldstein, T., Jiang, Y.G.: Towards transferable adversarial attacks on vision transformers. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 2668\u20132676 (2022)","DOI":"10.1609\/aaai.v36i3.20169"},{"key":"3_CR48","doi-asserted-by":"publisher","unstructured":"Wightman, R.: Pytorch image models (2019). https:\/\/doi.org\/10.5281\/zenodo.4414861. https:\/\/github.com\/rwightman\/pytorch-image-models","DOI":"10.5281\/zenodo.4414861"},{"key":"3_CR49","unstructured":"Xiang, C., Bhagoji, A.N., Sehwag, V., Mittal, P.: $$\\{$$PatchGuard$$\\}$$: a provably robust defense against adversarial patches via small receptive fields and masking. In: 30th USENIX Security Symposium (USENIX Security 2021), pp. 2237\u20132254 (2021)"},{"key":"3_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, J., Huang, Y., Wu, W., Lyu, M.R.: Transferable adversarial attacks on vision transformers with token gradient regularization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16415\u201316424 (2023)","DOI":"10.1109\/CVPR52729.2023.01575"},{"key":"3_CR51","unstructured":"Zhang, Y., Wei, Z., Sun, J., Sun, M.: Towards general conceptual model editing via adversarial representation engineering. arXiv preprint arXiv:2404.13752 (2024)"},{"key":"3_CR52","doi-asserted-by":"crossref","unstructured":"Zheng, S., et\u00a0al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"3_CR53","unstructured":"Zou, A., et\u00a0al.: Representation engineering: a top-down approach to AI transparency. arXiv preprint arXiv:2310.01405 (2023)"}],"container-title":["Lecture Notes in Computer Science","Advances in Visual Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-14492-8_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T07:08:01Z","timestamp":1768806481000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-14492-8_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032144911","9783032144928"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-14492-8_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"20 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISVC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Visual Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Las Vegas, NV","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","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":"17 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isvc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isvc.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}