{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:59:45Z","timestamp":1776887985044,"version":"3.51.2"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889743","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Assessing Robustness of Multi-Modal Large Language Models in Image Classification through Hierarchical WordNet-Based Evaluation"],"prefix":"10.1109","author":[{"given":"Chang","family":"Liu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}]},{"given":"Hai","family":"Chen","sequence":"additional","affiliation":[{"name":"Anhui Unversity,Hefei,China"}]},{"given":"Boxiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}]},{"given":"Shibao","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00040"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02196-3"},{"key":"ref6","first-page":"1","article-title":"Between words and characters: A brief history of open-vocabulary modeling and tokenization in nlp","author":"Mielke","year":"2021"},{"key":"ref7","first-page":"1","article-title":"Why are visually-grounded language models bad at image classification?","author":"Zhang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref9","first-page":"1","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"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_20"},{"key":"ref11","first-page":"216","article-title":"Mmbench: Is your multi-modal model an allaround player?","volume-title":"European conference on computer vision","author":"Liu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref14","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref17","first-page":"36789","article-title":"Viewfool: Evaluating the robustness of visual recognition to adversarial viewpoints","volume":"35","author":"Dong","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","first-page":"1","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"International Conference on Learning Representations","author":"Hendrycks"},{"key":"ref19","first-page":"1","article-title":"Learning robust global representations by penalizing local predictive power","volume":"32","author":"Wang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","first-page":"1","article-title":"How robust is google\u2019s bard to adversarial image attacks?","author":"Dong","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref24","article-title":"Openclip","author":"Ilharco","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref26","first-page":"1","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref28","first-page":"1","article-title":"To see is to believe: Prompting gpt-4v for better visual instruction tuning","author":"Wang","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"ref30","article-title":"Llavanext: Improved reasoning, ocr, and world knowledge","author":"Liu"},{"key":"ref31","first-page":"1","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","volume-title":"International Conference on Learning Representations","author":"Zhu"},{"key":"ref32","first-page":"1","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"ref34","first-page":"1","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3571946"},{"key":"ref36","first-page":"1","article-title":"Cogvlm: Visual expert for large language models","author":"Wang","year":"2023"},{"key":"ref37","first-page":"1","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"ref39","first-page":"1","article-title":"Internlm-xcomposer: A vision-language large model for advanced text-image comprehension and composition","author":"Zhang","year":"2023"},{"key":"ref40","first-page":"1","article-title":"Internlm-xcomposer2: Mastering free-form text-image composition and comprehension in vision-language large model","author":"Dong","year":"2024"},{"key":"ref41","first-page":"1","article-title":"Benchmarking trustworthiness of multimodal large language models: A comprehensive study","author":"Zhang","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889743.pdf?arnumber=10889743","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:08Z","timestamp":1774416308000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889743\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889743","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}