{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T10:11:31Z","timestamp":1774001491884,"version":"3.50.1"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276192"],"award-info":[{"award-number":["62276192"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62506268"],"award-info":[{"award-number":["62506268"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.inffus.2026.104183","type":"journal-article","created":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T00:25:58Z","timestamp":1769214358000},"page":"104183","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Adversarial perturbation for RGB-T tracking via intra-modal excavation and cross-modal collusion"],"prefix":"10.1016","volume":"131","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0744-1405","authenticated-orcid":false,"given":"Xinyu","family":"Xiang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2573-7838","authenticated-orcid":false,"given":"Xuying","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4238-5498","authenticated-orcid":false,"given":"Shengxiang","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9553-8628","authenticated-orcid":false,"given":"Qinglong","family":"Yan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4466-3765","authenticated-orcid":false,"given":"Tong","family":"Zou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5467-3428","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3264-3265","authenticated-orcid":false,"given":"Jiayi","family":"Ma","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104183_bib0001","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4282","article-title":"Siamrpn++: evolution of siamese visual tracking with very deep networks","author":"Li","year":"2019"},{"key":"10.1016\/j.inffus.2026.104183_bib0002","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"341","article-title":"Joint feature learning and relation modeling for tracking: a one-stream framework","author":"Ye","year":"2022"},{"key":"10.1016\/j.inffus.2026.104183_bib0003","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"990","article-title":"Cooling-shrinking attack: blinding the tracker with imperceptible noises","author":"Yan","year":"2020"},{"key":"10.1016\/j.inffus.2026.104183_bib0004","doi-asserted-by":"crossref","first-page":"1227","DOI":"10.1109\/TIFS.2023.3331899","article-title":"Pluggable attack for visual object tracking","volume":"19","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"issue":"3","key":"10.1016\/j.inffus.2026.104183_bib0005","doi-asserted-by":"crossref","first-page":"1958","DOI":"10.1109\/TPAMI.2024.3511621","article-title":"Divide-and-conquer: confluent triple-flow network for RGB-T salient object detection","volume":"47","author":"Tang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"12","key":"10.1016\/j.inffus.2026.104183_bib0006","doi-asserted-by":"crossref","first-page":"17973","DOI":"10.1109\/TNNLS.2023.3310118","article-title":"Image-specific information suppression and implicit local alignment for text-based person search","volume":"35","author":"Yan","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.inffus.2026.104183_bib0007","doi-asserted-by":"crossref","first-page":"5663","DOI":"10.1109\/TIFS.2025.3574976","article-title":"Modality-specific interactive attack for vision-Language pre-training models","volume":"20","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"issue":"6","key":"10.1016\/j.inffus.2026.104183_bib0008","doi-asserted-by":"crossref","first-page":"3880","DOI":"10.1109\/TCSVT.2021.3120479","article-title":"A simple and strong baseline for universal targeted attacks on siamese visual tracking","volume":"32","author":"Li","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.inffus.2026.104183_bib0009","series-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"2739","article-title":"Efficient universal shuffle attack for visual object tracking","author":"Liu","year":"2022"},{"issue":"4","key":"10.1016\/j.inffus.2026.104183_bib0010","doi-asserted-by":"crossref","first-page":"1705","DOI":"10.1007\/s10994-022-06252-2","article-title":"Dimba: discretely masked black-box attack in single object tracking","volume":"113","author":"Yin","year":"2024","journal-title":"Mach. Learn."},{"issue":"7","key":"10.1016\/j.inffus.2026.104183_bib0011","doi-asserted-by":"crossref","first-page":"6881","DOI":"10.1109\/TCSVT.2025.3541392","article-title":"Black-box explainability-guided adversarial attack for 3D object tracking","volume":"35","author":"Cheng","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.inffus.2026.104183_bib0012","series-title":"Proceedings of the IEEE International Conference on Robotics and Automation","first-page":"5893","article-title":"Ad2attack: adaptive adversarial attack on real-time uav tracking","author":"Fu","year":"2022"},{"issue":"7","key":"10.1016\/j.inffus.2026.104183_bib0013","doi-asserted-by":"crossref","first-page":"3173","DOI":"10.1109\/TCSVT.2023.3234266","article-title":"Only once attack: fooling the tracker with adversarial template","volume":"33","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"3","key":"10.1016\/j.inffus.2026.104183_bib0014","first-page":"3072","article-title":"Siammask: a framework for fast online object tracking and segmentation","volume":"45","author":"Hu","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104183_bib0015","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19258","article-title":"Hiptrack: visual tracking with historical prompts","author":"Cai","year":"2024"},{"key":"10.1016\/j.inffus.2026.104183_bib0016","doi-asserted-by":"crossref","first-page":"5613","DOI":"10.1109\/TIP.2021.3087341","article-title":"RGBT Tracking via multi-adapter network with hierarchical divergence loss","volume":"30","author":"Lu","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2026.104183_bib0017","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2831","article-title":"Attribute-based progressive fusion network for rgbt tracking","volume":"36","author":"Xiao","year":"2022"},{"key":"10.1016\/j.inffus.2026.104183_bib0018","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1016\/j.inffus.2022.10.034","article-title":"DIVFusion: darkness-free infrared and visible image fusion","volume":"91","author":"Tang","year":"2023","journal-title":"Inf. Fus."},{"key":"10.1016\/j.inffus.2026.104183_bib0019","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"26487","article-title":"Dispel darkness for better fusion: a controllable visual enhancer based on cross-modal conditional adversarial learning","author":"Zhang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104183_bib0020","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9516","article-title":"Visual prompt multi-modal tracking","author":"Zhu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104183_bib0021","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13630","article-title":"Bridging search region interaction with template for rgb-t tracking","author":"Hui","year":"2023"},{"key":"10.1016\/j.inffus.2026.104183_bib0022","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"927","article-title":"Bi-directional adapter for multimodal tracking","volume":"38","author":"Cao","year":"2024"},{"key":"10.1016\/j.inffus.2026.104183_bib0023","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"5189","article-title":"Generative-based fusion mechanism for multi-modal tracking","volume":"38","author":"Tang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104183_bib0024","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"26551","article-title":"Sdstrack: self-distillation symmetric adapter learning for multi-modal visual object tracking","author":"Hou","year":"2024"},{"key":"10.1016\/j.inffus.2026.104183_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112359","article-title":"Joint adversarial attack: an effective approach to evaluate robustness of 3D object tracking","volume":"172","author":"Cheng","year":"2026","journal-title":"Pattern Recogn."},{"key":"10.1016\/j.inffus.2026.104183_bib0026","doi-asserted-by":"crossref","first-page":"3144","DOI":"10.1109\/TMM.2025.3557613","article-title":"Adversarial geometric attacks for 3D point cloud object tracking","volume":"27","author":"Yao","year":"2025","journal-title":"IEEE Trans. Multimedia"},{"key":"10.1016\/j.inffus.2026.104183_bib0027","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10176","article-title":"One-shot adversarial attacks on visual tracking with dual attention","author":"Chen","year":"2020"},{"key":"10.1016\/j.inffus.2026.104183_bib0028","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"202","article-title":"Spark: spatial-aware online incremental attack against visual tracking","author":"Guo","year":"2020"},{"key":"10.1016\/j.inffus.2026.104183_bib0029","series-title":"Proceedings of the Conference on Robots and Vision","first-page":"1","article-title":"TrackPGD: efficient adversarial attack using object binary masks against robust transformer trackers","author":"Nokabadi","year":"2025"},{"key":"10.1016\/j.inffus.2026.104183_bib0030","doi-asserted-by":"crossref","first-page":"8824","DOI":"10.1109\/TMM.2024.3382473","article-title":"Context-guided black-box attack for visual tracking","volume":"26","author":"Huang","year":"2024","journal-title":"IEEE Trans. Multimedia"},{"key":"10.1016\/j.inffus.2026.104183_bib0031","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6709","article-title":"Iou attack: towards temporally coherent black-box adversarial attack for visual object tracking","author":"Jia","year":"2021"},{"issue":"3","key":"10.1016\/j.inffus.2026.104183_bib0032","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1007\/s11263-024-02226-0","article-title":"Robust deep object tracking against adversarial attacks","volume":"133","author":"Jia","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.inffus.2026.104183_bib0033","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.neucom.2022.08.071","article-title":"Diminishing-feature attack: the adversarial infiltration on visual tracking","volume":"509","author":"Suttapak","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.inffus.2026.104183_bib0034","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"413","article-title":"Universal, transferable adversarial perturbations for visual object trackers","author":"Nakka","year":"2022"},{"key":"10.1016\/j.inffus.2026.104183_bib0035","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8620","article-title":"Cross-modal stealth: a coarse-to-fine attack framework for RGB-T tracker","volume":"39","author":"Xiang","year":"2025"},{"key":"10.1016\/j.inffus.2026.104183_bib0036","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"22099","article-title":"ACAttack: adaptive cross attacking RGB-T tracker via multi-modal response decoupling","author":"Xiang","year":"2025"},{"key":"10.1016\/j.inffus.2026.104183_bib0037","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2019.106977","article-title":"RGB-T Object tracking: benchmark and baseline","volume":"96","author":"Li","year":"2019","journal-title":"Pattern Recogn."},{"key":"10.1016\/j.inffus.2026.104183_bib0038","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1109\/TIP.2021.3130533","article-title":"LasHerR: a large-scale high-diversity benchmark for RGBT tracking","volume":"31","author":"Li","year":"2022","journal-title":"IEEE Trans. Image Process."},{"issue":"12","key":"10.1016\/j.inffus.2026.104183_bib0039","doi-asserted-by":"crossref","first-page":"5743","DOI":"10.1109\/TIP.2016.2614135","article-title":"Learning collaborative sparse representation for grayscale-thermal tracking","volume":"25","author":"Li","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2026.104183_bib0040","article-title":"NOT-156: night object tracking using low-light and thermal infrared: from multi-modal common-aperture camera to benchmark datasets","volume":"63","author":"Sun","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104183_bib0041","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8886","article-title":"Visible-thermal UAV tracking: a large-scale benchmark and new baseline","author":"Zhang","year":"2022"},{"key":"10.1016\/j.inffus.2026.104183_bib0042","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"5734","article-title":"Xtrack: multimodal training boosts rgb-x video object trackers","author":"Tan","year":"2025"}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S156625352600062X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S156625352600062X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T07:24:59Z","timestamp":1773991499000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S156625352600062X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":42,"alternative-id":["S156625352600062X"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104183","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Adversarial perturbation for RGB-T tracking via intra-modal excavation and cross-modal collusion","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104183","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104183"}}