{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T06:45:41Z","timestamp":1767077141101,"version":"3.48.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,3]]},"DOI":"10.1109\/dicta68720.2025.11302451","type":"proceedings-article","created":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T18:36:22Z","timestamp":1767033382000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Robosurg: Resilience of Vision-Language Models Against Adversarial Attacks in Robotic Surgery"],"prefix":"10.1109","author":[{"given":"Ufaq","family":"Khan","sequence":"first","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence"}]},{"given":"Umair","family":"Nawaz","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence"}]},{"given":"Mustaqeem","family":"Khan","sequence":"additional","affiliation":[{"name":"United Arab Emirates University"}]},{"given":"Abdulmotaleb","family":"El Saddik","sequence":"additional","affiliation":[{"name":"University of Ottawa"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160403"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2023.3334618"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-39539-0_15"},{"key":"ref5","first-page":"337","article-title":"Smart malware that uses leaked control data of robotic applications: The case of Raven-II surgical robots","volume-title":"22nd International symposium on research in attacks, intrusions and defenses (RAID 2019)","author":"Chung"},{"key":"ref6","first-page":"3","article-title":"Explaining and harnessing adversarial examples","volume-title":"International Conference on Learning Representations (ICLR)","volume":"2","author":"Goodfellow"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02362"},{"key":"ref8","first-page":"1","article-title":"Surgical scene understanding in the era of foundation ai models: A comprehensive review","author":"Khan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73158-7_6"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"key":"ref11","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","volume":"2","author":"Li"},{"key":"ref12","first-page":"5","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume":"2","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"2","article-title":"Testtime backdoor attacks on multimodal large language models","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00016"},{"key":"ref15","first-page":"2","article-title":"An image is worth 1000 lies: Adversarial transferability across prompts on visionlanguage models","author":"Luo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref17","first-page":"1","article-title":"Im2text: Describing images using 1 million captioned photographs","volume":"24","author":"Ordonez","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00395"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43996-4_27"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16449-1_4"},{"key":"ref22","first-page":"5","article-title":"How much can clip benefit vision-and-language tasks?","volume":"2","author":"Shen","year":"2021","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00687"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16449-1_42"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104137"},{"key":"ref27","first-page":"2","article-title":"Avibench: Towards evaluating the robustness of large vision-language model on adversarial visualinstructions","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref30","first-page":"2","article-title":"On evaluating adversarial robustness of large vision-language models","volume":"36","author":"Zhao","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","start":{"date-parts":[[2025,12,3]]},"location":"Adelaide, Australia","end":{"date-parts":[[2025,12,5]]}},"container-title":["2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11302408\/11302416\/11302451.pdf?arnumber=11302451","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T06:41:04Z","timestamp":1767076864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11302451\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/dicta68720.2025.11302451","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]}}}