{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:24:04Z","timestamp":1776885844030,"version":"3.51.2"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":["IEEE Trans. Dependable and Secure Comput."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tdsc.2025.3601232","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:32:22Z","timestamp":1755801142000},"page":"7877-7889","source":"Crossref","is-referenced-by-count":5,"title":["A Multimodal Adversarial Attack Method via Frequency Domain Enhancement and Fine-Grained Cross-Modal Guidance"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4056-9755","authenticated-orcid":false,"given":"Yaguan","family":"Qian","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Information Engineering, Zhejiang University of Science and Technology, Hangzhou, China"}]},{"given":"Qinqin","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Information Engineering, Zhejiang University of Science and Technology, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1703-6090","authenticated-orcid":false,"given":"Qiqi","family":"Bao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Information Engineering, Zhejiang University of Science and Technology, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4268-372X","authenticated-orcid":false,"given":"Shouling","family":"Ji","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5974-1589","authenticated-orcid":false,"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Ministry of Education Key Lab for Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’an, China"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang Key Laboratory of Artificial Intelligence of Things (AIoT) Network and Data Security, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7546-852X","authenticated-orcid":false,"given":"Zhaoquan","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0791-189X","authenticated-orcid":false,"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[{"name":"Center for Biometrics and Security Research and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00427"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref6","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"Xu","year":"2015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.080"},{"key":"ref9","article-title":"Adversarial training via multi-guidance and historical memory enhancement","volume-title":"Neurocomputing","volume":"619","author":"Zhao","year":"2025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3580116"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_25"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00416"},{"key":"ref14","article-title":"A fourier perspective on model robustness in computer vision","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yin"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00871"},{"key":"ref16","article-title":"Towards frequency-based explanation for robust CNN","author":"Wang","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3430508"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.500"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547801"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/470"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1369-5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref27","article-title":"Towards deep learning models resistant to adversarial attacks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Madry"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00102"},{"key":"ref29","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"ref31","article-title":"Low frequency adversarial perturbation","author":"Guo","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_28"},{"key":"ref33","article-title":"A fourier perspective of feature extraction and adversarial robustness","volume-title":"Proc. 33rd Int. Joint Conf. Artif. Intell.","author":"Zhang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00393"},{"key":"ref35","article-title":"BERT: A review of applications in natural language processing and understanding","author":"Koroteev","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref37","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"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref39","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref40","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization Branches Out","author":"Chin-Yew"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref43","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref44","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dai"}],"container-title":["IEEE Transactions on Dependable and Secure Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8858\/11242243\/11134075.pdf?arnumber=11134075","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T21:00:55Z","timestamp":1763154055000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11134075\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":44,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tdsc.2025.3601232","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":[[2025,11]]}}}