{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T09:50:26Z","timestamp":1780566626701,"version":"3.54.1"},"publisher-location":"Cham","reference-count":65,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732010","type":"print"},{"value":"9783031732027","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73202-7_7","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T14:16:32Z","timestamp":1732112192000},"page":"110-127","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Robustness Tokens: Towards Adversarial Robustness of\u00a0Transformers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0809-6978","authenticated-orcid":false,"given":"Brian","family":"Pulfer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6461-734X","authenticated-orcid":false,"given":"Yury","family":"Belousov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0416-9674","authenticated-orcid":false,"given":"Slava","family":"Voloshynovskiy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: a video vision transformer (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"7_CR2","doi-asserted-by":"publisher","unstructured":"Assran, M., et al.: Masked Siamese networks for label-efficient learning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13691, pp. 456\u2013473 Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19821-2_26","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Assran, M., et al.: Self-supervised learning from images with a joint-embedding predictive architecture. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15619\u201315629 (June 2023)","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"7_CR4","unstructured":"Awais, M., et al.: Foundational models defining a new era in vision: a survey and outlook. arXiv preprint arXiv:2307.13721 (2023)"},{"key":"7_CR5","unstructured":"Bahri, Y., Dyer, E., Kaplan, J., Lee, J., Sharma, U.: Explaining neural scaling laws. arXiv preprint arXiv:2102.06701 (2021)"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Bai, T., Luo, J., Zhao, J., Wen, B., Wang, Q.: Recent advances in adversarial training for adversarial robustness. arXiv preprint arXiv:2102.01356 (2021)","DOI":"10.24963\/ijcai.2021\/591"},{"key":"7_CR7","unstructured":"Balestriero, R., et\u00a0al.: A cookbook of self-supervised learning. arXiv preprint arXiv:2304.12210 (2023)"},{"key":"7_CR8","first-page":"1196","volume":"35","author":"Y Ban","year":"2022","unstructured":"Ban, Y., Dong, Y.: Pre-trained adversarial perturbations. Adv. Neural Inf. Process. Syst. 35, 1196\u20131209 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"7_CR9","unstructured":"Bommasani, R., et\u00a0al.: On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)"},{"key":"7_CR10","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), pp. 39\u201357. IEEE (2017)","DOI":"10.1109\/SP.2017.49"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Context autoencoder for self-supervised representation learning (2022)","DOI":"10.1109\/CVPR52729.2023.02178"},{"key":"7_CR12","unstructured":"Croce, F., et al.: Robustbench: a standardized adversarial robustness benchmark. arXiv preprint arXiv:2010.09670 (2020)"},{"key":"7_CR13","unstructured":"Croce, F., Hein, M.: Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. In: International Conference on Machine Learning, pp. 2206\u20132216. PMLR (2020)"},{"key":"7_CR14","unstructured":"Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need registers (2023)"},{"key":"7_CR15","unstructured":"Demontis, A., et al.: Why do adversarial attacks transfer? Explaining transferability of evasion and poisoning attacks. In: 28th USENIX Security Symposium (USENIX Security 19), pp. 321\u2013338 (2019)"},{"key":"7_CR16","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":"7_CR17","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: QLORA: efficient finetuning of quantized llms. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"7_CR18","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":"7_CR19","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale (2021)"},{"key":"7_CR20","unstructured":"El-Nouby, A., et al.: Scalable pre-training of large autoregressive image models (2024)"},{"key":"7_CR21","unstructured":"Fort, S.: Adversarial examples for the openai clip in its zero-shot classification regime and their semantic generalization, January 2021. https:\/\/stanislavfort.github.io\/2021\/01\/12\/OpenAI_CLIP_adversarial_examples.html"},{"key":"7_CR22","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)"},{"key":"7_CR23","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces (2023)"},{"key":"7_CR24","unstructured":"Hatamizadeh, A., Ranzinger, M., Lan, S., Alvarez, J.M., Fidler, S., Kautz, J.: Vir: towards efficient vision retention backbones (2024)"},{"key":"7_CR25","unstructured":"He, J., Zhou, C., Ma, X., Berg-Kirkpatrick, T., Neubig, G.: Towards a unified view of parameter-efficient transfer learning. arXiv preprint arXiv:2110.04366 (2021)"},{"key":"7_CR26","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 (CVPR), pp. 16000\u201316009 (June 2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"7_CR27","unstructured":"Hendrycks, D., Mazeika, M., Kadavath, S., Song, D.: Using self-supervised learning can improve model robustness and uncertainty. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a032. Curran Associates, Inc. (2019). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/a2b15837edac15df90721968986f7f8e-Paper.pdf"},{"key":"7_CR28","unstructured":"Hestness, J., et al.: Deep learning scaling is predictable, empirically. arXiv preprint arXiv:1712.00409 (2017)"},{"issue":"8","key":"7_CR29","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"7_CR30","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"7_CR31","doi-asserted-by":"publisher","unstructured":"Ilharco, G., et al.: Openclip (2021). https:\/\/doi.org\/10.5281\/zenodo.5143773","DOI":"10.5281\/zenodo.5143773"},{"key":"7_CR32","unstructured":"Inkawhich, N., McDonald, G., Luley, R.: Adversarial attacks on foundational vision models (2023)"},{"key":"7_CR33","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"7_CR34","unstructured":"Jiang, X., Ge, Y., Ge, Y., Yuan, C., Shan, Y.: Supervised fine-tuning in turn improves visual foundation models. arXiv preprint arXiv:2401.10222 (2024)"},{"key":"7_CR35","unstructured":"Kim, H.: Torchattacks: a pytorch repository for adversarial attacks. arXiv preprint arXiv:2010.01950 (2020)"},{"key":"7_CR36","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Li, L.H., et\u00a0al.: Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10965\u201310975 (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Li, Y., Fan, H., Hu, R., Feichtenhofer, C., He, K.: Scaling language-image pre-training via masking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23390\u201323400 (2023)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"7_CR40","unstructured":"Lian, C., Zhou, H.Y., Yu, Y., Wang, L.: Less could be better: parameter-efficient fine-tuning advances medical vision foundation models. arXiv preprint arXiv:2401.12215 (2024)"},{"key":"7_CR41","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"7_CR42","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks (2019)"},{"key":"7_CR43","unstructured":"Mann, B., et\u00a0al.: Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)"},{"key":"7_CR44","unstructured":"Miller, E.: Attention is off by one (2023). https:\/\/www.evanmiller.org\/attention-is-off-by-one.html"},{"key":"7_CR45","doi-asserted-by":"crossref","unstructured":"Moosavi-Dezfooli, S.M., Fawzi, A., Frossard, P.: Deepfool: a simple and accurate method to fool deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2574\u20132582 (2016)","DOI":"10.1109\/CVPR.2016.282"},{"key":"7_CR46","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 427\u2013436 (2015)","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"7_CR47","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision (2023)"},{"key":"7_CR48","unstructured":"Peng, B., et\u00a0al.: Rwkv: reinventing rnns for the transformer era. arXiv preprint arXiv:2305.13048 (2023)"},{"key":"7_CR49","unstructured":"Peng, Z., Dong, L., Bao, H., Ye, Q., Wei, F.: Beit v2: masked image modeling with vector-quantized visual tokenizers (2022)"},{"key":"7_CR50","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)"},{"key":"7_CR51","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518. PMLR (2023)"},{"key":"7_CR52","unstructured":"Rando, J., Naimi, N., Baumann, T., Mathys, M.: Exploring adversarial attacks and defenses in vision transformers trained with dino (2022). https:\/\/arxiv.org\/abs\/2206.06761"},{"key":"7_CR53","doi-asserted-by":"crossref","unstructured":"Schlarmann, C., Hein, M.: On the adversarial robustness of multi-modal foundation models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) Workshops, pp. 3677\u20133685, October 2023","DOI":"10.1109\/ICCVW60793.2023.00395"},{"key":"7_CR54","unstructured":"Sitawarin, C., Chang, J., Huang, D., Altoyan, W., Wagner, D.: Defending against transfer attacks from public models (2023)"},{"key":"7_CR55","unstructured":"Sun, M., Chen, X., Kolter, J.Z., Liu, Z.: Massive activations in large language models (2024)"},{"key":"7_CR56","unstructured":"Sun, Y., et al.: Retentive network: a successor to transformer for large language models. arXiv preprint arXiv:2307.08621 (2023)"},{"key":"7_CR57","doi-asserted-by":"publisher","unstructured":"Touvron, H., Cord, M., J\u00e9gou, H.: DeiT III: revenge of the ViT. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13684, pp. 516\u2013533. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20053-3_30","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"7_CR58","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a030. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"7_CR59","unstructured":"Xiao, G., Tian, Y., Chen, B., Han, S., Lewis, M.: Efficient streaming language models with attention sinks (2023)"},{"key":"7_CR60","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: simple and efficient design for semantic segmentation with transformers. Adv. Neural Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"7_CR61","first-page":"25464","volume":"35","author":"B Yuan","year":"2022","unstructured":"Yuan, B., et al.: Decentralized training of foundation models in heterogeneous environments. Adv. Neural Inf. Process. Syst. 35, 25464\u201325477 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"7_CR62","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.544"},{"key":"7_CR63","unstructured":"Zhou, J., et al.: Training and serving system of foundation models: a comprehensive survey. arXiv preprint arXiv:2401.02643 (2024)"},{"key":"7_CR64","unstructured":"Zhou, J., et al.: iBOT: image bert pre-training with online tokenizer (2022)"},{"key":"7_CR65","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision mamba: efficient visual representation learning with bidirectional state space model. arXiv preprint arXiv:2401.09417 (2024)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73202-7_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T15:06:54Z","timestamp":1732115214000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73202-7_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031732010","9783031732027"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73202-7_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}