{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T11:31:05Z","timestamp":1764588665312,"version":"3.45.0"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11229253","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Manipulating the Bounding Box: Multimodal Controlled Backdoor Attacks on 3D Visual Grounding Models"],"prefix":"10.1109","author":[{"given":"Xiayue","family":"Zhang","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology"}]},{"given":"Huashuo","family":"Lei","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}]},{"given":"Daizong","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University"}]},{"given":"Xiaoye","family":"Qu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}]},{"given":"Xiang","family":"Fang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}]},{"given":"Runwei","family":"Guan","sequence":"additional","affiliation":[{"name":"University of Liverpool"}]},{"given":"Keyan","family":"Jin","sequence":"additional","affiliation":[{"name":"University of Granada"}]}],"member":"263","reference":[{"article-title":"A survey of efficient reasoning for large reasoning models: Language, multimodality, and beyond","year":"2025","author":"Qu","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28145"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3634749"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_17"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3334019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612038"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25251"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3223725"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.41"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20058"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16307"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.062"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00452"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwad141"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.404"},{"article-title":"Textsquare: Scaling up text-centric visual instruction tuning","year":"2024","author":"Tang","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547787"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40994-3_25"},{"article-title":"Intriguing properties of neural networks","year":"2013","author":"Szegedy","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78113-1_17"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3543050"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3584895"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611902"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680614"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680758"},{"article-title":"Label-consistent backdoor attacks","year":"2019","author":"Turner","key":"ref28"},{"article-title":"Hard-label black-box attacks on 3d point clouds","year":"2024","author":"Liu","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3592935"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28146"},{"key":"ref32","article-title":"Pandora\u2019s box: Towards building universal attackers against real-world large vision-language models","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681105"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_25"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3339130"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01319"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3193449"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3304896"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3182979"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3485832.3485837"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00370"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475397"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"ref44","article-title":"Languagerefer: Spatial-language model for 3d visual grounding","author":"Roh","year":"2022","journal-title":"CoRL"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00750"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/361237.361242"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01596"},{"article-title":"D3net: A speaker-listener architecture for semi-supervised dense captioning and visual grounding in rgb-d scans","year":"2021","author":"Chen","key":"ref50"},{"article-title":"Learning point-language hierarchical alignment for 3d visual grounding","year":"2022","author":"Chen","key":"ref51"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01397"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11229253.pdf?arnumber=11229253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:14:33Z","timestamp":1763190873000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11229253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11229253","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}