{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T19:16:48Z","timestamp":1776799008911,"version":"3.51.2"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62425603"],"award-info":[{"award-number":["62425603"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005145","name":"Basic Research Program of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20243018"],"award-info":[{"award-number":["BK20243018"]}],"id":[{"id":"10.13039\/501100005145","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Dependable and Secure Comput."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tdsc.2025.3625576","type":"journal-article","created":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T18:07:54Z","timestamp":1761588474000},"page":"2198-2214","source":"Crossref","is-referenced-by-count":5,"title":["Gradient Pruning Interactive Attack for Vision-Language Pre-Training Models"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2617-9665","authenticated-orcid":false,"given":"Haiqi","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6973-8121","authenticated-orcid":false,"given":"Hao","family":"Tang","sequence":"additional","affiliation":[{"name":"Centre for Smart Health, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6249-5596","authenticated-orcid":false,"given":"Yanpeng","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5341-5985","authenticated-orcid":false,"given":"Zechao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00293"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3574976"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/93"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132068"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25452"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3511621"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.500"},{"key":"ref11","article-title":"Transferable perturbations of deep feature distributions","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Inkawhich","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s42452-021-04148-9"},{"key":"ref13","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.01.071"},{"key":"ref15","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_25"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_42"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref25","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref26","first-page":"37484","article-title":"Singular value fine-tuning: Few-shot segmentation requires few-parameters fine-tuning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Sun","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02218"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547801"},{"key":"ref29","first-page":"52936","article-title":"VLATTACk: Multimodal adversarial attacks on vision-language tasks via pre-trained models","volume-title":"Proc. 37th Int. Neural Inf. Process. Syst.","author":"Yin","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28034"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3235495"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3310118"},{"key":"ref33","article-title":"Intriguing properties of neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Szegedy","year":"2014"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2023.3289298"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2023.3241428"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2019.2929047"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2024.3353302"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2023.3285015"},{"key":"ref39","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goodfellow","year":"2015"},{"key":"ref40","article-title":"Nesterov accelerated gradient and scale invariance for adversarial attacks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6311"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2023.3339802"},{"key":"ref43","first-page":"653","article-title":"On adversarial examples for character-level neural machine translation","volume-title":"Proc. Int. Conf. Comput. Linguistic","author":"Ebrahimi","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23138"},{"key":"ref45","article-title":"Adversarial glue: A multi-task benchmark for robustness evaluation of language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2021"},{"key":"ref46","first-page":"10791","article-title":"Cross-modal learning with adversarial samples","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Li","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00222"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403084"},{"key":"ref49","article-title":"OT-ATTACK: Enhancing adversarial transferability of vision-language models via optimal transport optimization","author":"Han","year":"2023"},{"key":"ref50","article-title":"SA-ATTACK: Improving adversarial transferability of vision-language pre-training models via self-augmentation","author":"He","year":"2023"},{"key":"ref51","article-title":"Improving adversarial transferability of visual-language pre-training models through collaborative multimodal interaction","author":"Fu","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681184"},{"key":"ref53","article-title":"Feedback-based modal mutual search for attacking vision-language pre-training models","author":"Ding","year":"2024"},{"key":"ref54","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","volume-title":"Proc. Int. Conf. Learn. Recognit.","author":"Keskar","year":"2017"},{"key":"ref55","article-title":"Sharpness-aware minimization for efficiently improving generalization","volume-title":"Proc. Int. Conf. Learn. Recognit.","author":"Foret","year":"2021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref58","first-page":"23296","article-title":"Intriguing properties of vision transformers","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Naseer","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3202690"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3617592"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2852750"},{"key":"ref63","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref64","article-title":"Qwen technical report","author":"Bai","year":"2023"}],"container-title":["IEEE Transactions on Dependable and Secure Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8858\/11434575\/11217326.pdf?arnumber=11217326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T01:15:19Z","timestamp":1773710119000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11217326\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":64,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tdsc.2025.3625576","relation":{},"ISSN":["1545-5971","1941-0018","2160-9209"],"issn-type":[{"value":"1545-5971","type":"print"},{"value":"1941-0018","type":"electronic"},{"value":"2160-9209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}