{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:15:58Z","timestamp":1774419358167,"version":"3.50.1"},"reference-count":37,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889297","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Robust CLIP-Guided Deep Thinking: A Two-Stage Optimization Strategy for Enhancing Adversarial Robustness and Reliability in LVLMs"],"prefix":"10.1109","author":[{"given":"Yize","family":"Sui","sequence":"first","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China,410073"}]},{"given":"Wanrong","family":"Huang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China,410073"}]},{"given":"Wenjing","family":"Yang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China,410073"}]},{"given":"Chaofan","family":"Zhao","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China,410073"}]},{"given":"Jing","family":"Ren","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China,410073"}]},{"given":"Ji","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China,410073"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4222-0"},{"key":"ref3","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"ref4","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":"ref5","article-title":"Universal and transferable adversarial attacks on aligned language models","author":"Zou","year":"2023"},{"key":"ref6","article-title":"How robust is google\u2019s bard to adversarial image attacks?","author":"Dong","year":"2023"},{"key":"ref7","article-title":"Evaluation and analysis of hallucination in large vision-language models","author":"Wang","year":"2023"},{"key":"ref8","article-title":"Analyzing and mitigating object hallucination in large vision-language models","author":"Zhou","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00257"},{"key":"ref10","article-title":"Beyond hallucinations: Enhancing lvlms through hallucination-aware direct preference optimization","author":"Zhao","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"ref12","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017"},{"key":"ref13","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","volume-title":"International conference on machine learning","author":"Zhang"},{"key":"ref14","first-page":"2958","article-title":"Adversarial weight perturbation helps robust generalization","volume":"33","author":"Wu","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Understanding zero-shot adversarial robustness for large-scale models","author":"Mao","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28338"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4251-x"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463257"},{"key":"ref19","first-page":"2206","article-title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","volume-title":"International conference on machine learning","author":"Croce"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"issue":"3","key":"ref22","first-page":"8","article-title":"Improving image generation with better captions","volume-title":"Computer Science. https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf","volume":"2","author":"Betker","year":"2023"},{"key":"ref23","article-title":"Openflamingo: An open-source framework for training large autoregressive vision-language models","author":"Awadalla","year":"2023"},{"key":"ref24","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Introducing mpt-7b: A new standard for open-source, commercially usable llms","year":"2023"},{"issue":"3","key":"ref26","first-page":"6","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","volume":"2","author":"Chiang","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref34","article-title":"The curious case of neural text degeneration","author":"Holtzman","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref36","article-title":"Dola: Decoding by contrasting layers improves factuality in large language models","author":"Chuang","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53302-0_3"}],"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\/10889297.pdf?arnumber=10889297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:28Z","timestamp":1774416148000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889297\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889297","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}