{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T13:10:12Z","timestamp":1759065012235,"version":"3.44.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032065926","type":"print"},{"value":"9783032065933","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"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\/978-3-032-06593-3_7","type":"book-chapter","created":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T12:37:45Z","timestamp":1759063065000},"page":"69-80","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SPARTA: Spectral Prompt Agnostic Adversarial Attack on\u00a0Medical Vision-Language Models"],"prefix":"10.1007","author":[{"given":"Asif","family":"Hanif","sequence":"first","affiliation":[]},{"given":"Zaigham","family":"Zaheer","sequence":"additional","affiliation":[]},{"given":"Salman","family":"Khan","sequence":"additional","affiliation":[]},{"given":"Fahad Shahbaz","family":"Khan","sequence":"additional","affiliation":[]},{"given":"Rao","family":"Anwer","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Clusmann, J., et al.: Prompt injection attacks on vision language models in oncology. Nat. Commun. 16(1), 1239 (2025)","DOI":"10.1038\/s41467-024-55631-x"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Duan, R., Chen, Y., Niu, D., Yang, Y., Qin, A.K., He, Y.: Advdrop: adversarial attack to DNNS by dropping information. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7506\u20137515 (2021)","DOI":"10.1109\/ICCV48922.2021.00741"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Eslami, S., Meinel, C., De\u00a0Melo, G.: Pubmedclip: how much does clip benefit visual question answering in the medical domain? In: Findings of the Association for Computational Linguistics: EACL 2023, pp. 1151\u20131163 (2023)","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"issue":"6433","key":"7_CR4","doi-asserted-by":"publisher","first-page":"1287","DOI":"10.1126\/science.aaw4399","volume":"363","author":"SG Finlayson","year":"2019","unstructured":"Finlayson, S.G., Bowers, J.D., Ito, J., Zittrain, J.L., Beam, A.L., Kohane, I.S.: Adversarial attacks on medical machine learning. Science 363(6433), 1287\u20131289 (2019)","journal-title":"Science"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Georgescu, M.I., et al.: Multimodal multi-head convolutional attention with various kernel sizes for medical image super-resolution. In: 2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2194\u20132204 (2022)","DOI":"10.1109\/WACV56688.2023.00223"},{"key":"7_CR6","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)"},{"key":"7_CR7","unstructured":"Gu, J., et\u00a0al.: A survey on transferability of adversarial examples across deep neural networks. arXiv preprint arXiv:2310.17626 (2023)"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Hanif, A., Naseer, M., Khan, S., Khan, F.S.: On frequency domain adversarial vulnerabilities of volumetric medical image segmentation. In: 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI), pp. 01\u201305. IEEE (2025)","DOI":"10.1109\/ISBI60581.2025.10981075"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Hanif, A., Naseer, M., Khan, S., Shah, M., Khan, F.S.: Frequency domain adversarial training for robust volumetric medical segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 457\u2013467. Springer (2023)","DOI":"10.1007\/978-3-031-43895-0_43"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Hanif, A., et al.: Baple: backdoor attacks on medical foundational models using prompt learning. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 443\u2013453. Springer (2024)","DOI":"10.1007\/978-3-031-72390-2_42"},{"key":"7_CR11","doi-asserted-by":"publisher","first-page":"1430984","DOI":"10.3389\/frai.2024.1430984","volume":"7","author":"I Hartsock","year":"2024","unstructured":"Hartsock, I., Rasool, G.: Vision-language models for medical report generation and visual question answering: a review. Front. Artif. Intell. 7, 1430984 (2024)","journal-title":"Front. Artif. Intell."},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"He, X., Zhang, Y., Mou, L., Xing, E., Xie, P.: Pathvqa: 30000+ questions for medical visual question answering. arXiv preprint arXiv:2003.10286 (2020)","DOI":"10.36227\/techrxiv.13127537"},{"key":"7_CR13","unstructured":"Huang, J., Zhang, J.: A survey on evaluation of multimodal large language models. arXiv preprint arXiv:2408.15769 (2024)"},{"key":"7_CR14","unstructured":"Imam, R., Hanif, A., Zhang, J., Dawoud, K.W., Kementchedjhieva, Y., Yaqub, M.: Noise is an efficient learner for zero-shot vision-language models. arXiv preprint arXiv:2502.06019 (2025)"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Imam, R., Marew, R., Yaqub, M.: On the robustness of medical vision-language models: Are they truly generalizable? In: Annual Conference on Medical Image Understanding and Analysis, pp. 233\u2013256. Springer (2025)","DOI":"10.1007\/978-3-031-98688-8_17"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Khan, U., Nawaz, U., Sheikh, T.T., Hanif, A., Yaqub, M.: Guardian: guarding against uncertainty and adversarial risks in robot-assisted surgeries. In: International Workshop on Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, pp. 59\u201369. Springer (2024)","DOI":"10.1007\/978-3-031-73158-7_6"},{"issue":"1","key":"7_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.251","volume":"5","author":"JJ Lau","year":"2018","unstructured":"Lau, J.J., Gayen, S., Ben Abacha, A., Demner-Fushman, D.: A dataset of clinically generated visual questions and answers about radiology images. Sci. Data 5(1), 1\u201310 (2018)","journal-title":"Sci. Data"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Llava-med: training a large language-and-vision assistant for biomedicine in one day. In: Advances in Neural Information Processing Systems, vol. 36 (2024)","DOI":"10.32388\/VLXB6M"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Li, M., Deng, C., Li, T., Yan, J., Gao, X., Huang, H.: Towards transferable targeted attack. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 641\u2013649 (2020)","DOI":"10.1109\/CVPR42600.2020.00072"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Xu, L., Ma, L., Yang, Y., Wu, X.M.: Slake: a semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1650\u20131654. IEEE (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Liu, D., Yang, M., Qu, X., Zhou, P., Cheng, Y., Hu, W.: A survey of attacks on large vision-language models: Resources, advances, and future trends. arXiv preprint arXiv:2407.07403 (2024)","DOI":"10.1109\/TNNLS.2025.3592935"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Long, Y., et al.: Frequency domain model augmentation for adversarial attack. In: European Conference on Computer Vision, pp. 549\u2013566. Springer (2022)","DOI":"10.1007\/978-3-031-19772-7_32"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Lu, Y., Jia, Y., Wang, J., Li, B., Chai, W., Carin, L., Velipasalar, S.: Enhancing cross-task black-box transferability of adversarial examples with dispersion reduction. In: Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition, pp. 940\u2013949 (2020)","DOI":"10.1109\/CVPR42600.2020.00102"},{"key":"7_CR24","unstructured":"Luo, H., Gu, J., Liu, F., Torr, P.: An image is worth 1000 lies: transferability of adversarial images across prompts on vision-language models. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"7_CR25","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":"7_CR26","unstructured":"Malik, H.S., et al.: On evaluating adversarial robustness of volumetric medical segmentation models. arXiv preprint arXiv:2406.08486 (2024)"},{"issue":"12","key":"7_CR27","doi-asserted-by":"publisher","first-page":"6070","DOI":"10.1109\/JBHI.2022.3207502","volume":"26","author":"JH Moon","year":"2022","unstructured":"Moon, J.H., Lee, H., Shin, W., Kim, Y.H., Choi, E.: Multi-modal understanding and generation for medical images and text via vision-language pre-training. IEEE J. Biomed. Health Inform. 26(12), 6070\u20136080 (2022)","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"7_CR28","unstructured":"Moor, M., et al.: Med-flamingo: a multimodal medical few-shot learner. In: Machine Learning for Health (ML4H), pp. 353\u2013367. PMLR (2023)"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Moosavi-Dezfooli, S.M., Fawzi, A., Fawzi, O., Frossard, P.: Universal adversarial perturbations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1765\u20131773 (2017)","DOI":"10.1109\/CVPR.2017.17"},{"key":"7_CR30","unstructured":"Naseer, M.M., Khan, S.H., Khan, M.H., Shahbaz\u00a0Khan, F., Porikli, F.: Cross-domain transferability of adversarial perturbations. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Naseer, M., Khan, S.H., Hayat, M., Khan, F.S., Porikli, F.M.: On generating transferable targeted perturbations. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7688\u20137697 (2021)","DOI":"10.1109\/ICCV48922.2021.00761"},{"key":"7_CR32","unstructured":"Naseer, M., Ranasinghe, K., Khan, S.S., Khan, F.S., Porikli, F.M.: On improving adversarial transferability of vision transformers. arXiv abs\/2106.04169 (2021)"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Qi, X., Huang, K., Panda, A., Henderson, P., Wang, M., Mittal, P.: Visual adversarial examples jailbreak aligned large language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 21527\u201321536 (2024)","DOI":"10.1609\/aaai.v38i19.30150"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Ranasinghe, K., Naseer, M., Hayat, M., Khan, S.H., Khan, F.S.: Orthogonal projection loss. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 12313\u201312323 (2021)","DOI":"10.1109\/ICCV48922.2021.01211"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Saad, M.A., Bovik, A.C., Charrier, C.: Blind image quality assessment: a natural scene statistics approach in the DCT domain. IEEE Trans. Image Process. 21(8), 3339\u20133352 (2012)","DOI":"10.1109\/TIP.2012.2191563"},{"key":"7_CR36","unstructured":"Schlarmann, C., Singh, N.D., Croce, F., Hein, M.: Robust clip: unsupervised adversarial fine-tuning of vision embeddings for robust large vision-language models. arXiv preprint arXiv:2402.12336 (2024)"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Thawkar, O., et al.: Xraygpt: chest radiographs summarization using medical vision-language models. arXiv preprint arXiv:2306.07971 (2023)","DOI":"10.18653\/v1\/2024.bionlp-1.35"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Wei, Z., Chen, J., Wu, Z., Jiang, Y.G.: Cross-modal transferable adversarial attacks from images to videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15064\u201315073 (2022)","DOI":"10.1109\/CVPR52688.2022.01464"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Wu, J., Gan, W., Chen, Z., Wan, S., Philip, S.Y.: Multimodal large language models: a survey. In: 2023 IEEE International Conference on Big Data (BigData), pp. 2247\u20132256. IEEE (2023)","DOI":"10.1109\/BigData59044.2023.10386743"},{"key":"7_CR40","unstructured":"Xia, P., et al.: Cares: a comprehensive benchmark of trustworthiness in medical vision language models. In: Advances in Neural Information Processing Systems, vol. 37, pp. 140334\u2013140365 (2025)"},{"key":"7_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, J., Huang, J., Jin, S., Lu, S.: Vision-language models for vision tasks: a survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"7_CR42","unstructured":"Zhang, X., et al.: PMC-VQA: visual instruction tuning for medical visual question answering. arXiv preprint arXiv:2305.10415 (2023)"},{"issue":"9","key":"7_CR43","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"}],"container-title":["Lecture Notes in Computer Science","Uncertainty for Safe Utilization of Machine Learning in Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06593-3_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T12:37:54Z","timestamp":1759063074000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06593-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"ISBN":["9783032065926","9783032065933"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06593-3_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,29]]},"assertion":[{"value":"29 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"UNSURE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Uncertainty for Safe Utilization of Machine Learning in Medical Imaging","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","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":"27 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"unsure2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/unsuremiccai.github.io","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}