{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:38:17Z","timestamp":1771922297614,"version":"3.50.1"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccvw69036.2025.00311","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:44:02Z","timestamp":1771879442000},"page":"2976-2985","source":"Crossref","is-referenced-by-count":0,"title":["Watch, Listen, Understand, Mislead: Tri-Modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation"],"prefix":"10.1109","author":[{"given":"Sahid Hossain","family":"Mustakim","sequence":"first","affiliation":[{"name":"United International University,Bangladesh"}]},{"given":"S M Jishanul","family":"Islam","sequence":"additional","affiliation":[{"name":"United International University,Bangladesh"}]},{"given":"Ummay Maria","family":"Muna","sequence":"additional","affiliation":[{"name":"BRAC University,India"}]},{"given":"Montasir","family":"Chowdhury","sequence":"additional","affiliation":[{"name":"United International University,Bangladesh"}]},{"given":"Mohammad Jawwadul","family":"Islam","sequence":"additional","affiliation":[{"name":"United International University,Bangladesh"}]},{"given":"Sadia","family":"Ahmmed","sequence":"additional","affiliation":[{"name":"University of British Columbia,Canada"}]},{"given":"Tashfia","family":"Sikder","sequence":"additional","affiliation":[{"name":"Bangladesh University of Professionals,Bangladesh"}]},{"given":"Syed Tasdid Azam","family":"Dhrubo","sequence":"additional","affiliation":[{"name":"University of Alberta,Canada"}]},{"given":"Swakkhar","family":"Shatabda","sequence":"additional","affiliation":[{"name":"BRAC University,India"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Reference-guided verdict: Llms-as-judges in automatic evaluation of free-form text","author":"Badshah","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","volume-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02215"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02243"},{"key":"ref6","article-title":"From compliance to exploitation: Jailbreak prompt attacks on multimodal llms","author":"Chiu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v11i1.14955"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3456150"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34568"},{"key":"ref11","volume-title":"Agent smith: a single image can jailbreak one million multimodal llm agents exponentially fast","author":"Gu","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01852"},{"key":"ref13","article-title":"Llm-as-a-judge: Reassessing the performance of llms in extractive qa","author":"Ho","year":"2025","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Curiosity-driven red-teaming for large language models","author":"Hong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Videojail: Exploiting video-modality vulnerabilities for jail-break attacks on multimodal large language models","volume-title":"ICLR 2025 Workshop on Building Trust in Language Models and Applications","author":"Hu","year":"2025"},{"key":"ref16","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02786"},{"key":"ref18","author":"Jiang","year":"2023","journal-title":"Mistral 7b"},{"key":"ref19","article-title":"Mixtral of experts","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Trust or escalate: Llm judges with provable guarantees for human agreement","author":"Jung","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","first-page":"2611","article-title":"The hateful memes challenge: Detecting hate speech in multimodal memes","volume":"33","author":"Kiela","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Learning diverse attacks on large language models for robust red-teaming and safety tuning","author":"Lee","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Fmm-attack: A flow-based multi-modal adversarial attack on video-based llms","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.198"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_11"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.360"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref28","author":"Liu","year":"2023","journal-title":"Visual instruction tuning"},{"key":"ref29","article-title":"Prompt injection attack against llm-integrated applications","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681379"},{"key":"ref31","volume-title":"LLaMA 4: Advancing Multimodal Intelligence","year":"2025"},{"key":"ref32","article-title":"Jailbreaking attack against multimodal large language model","author":"Niu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","volume-title":"Gpt-4o system card","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.298"},{"key":"ref35","article-title":"Vision-llms can fool themselves with self-generated typographic attacks","author":"Qraitem","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00395"},{"key":"ref37","volume-title":"Gemini: A family of highly capable multimodal models","year":"2025"},{"key":"ref38","volume-title":"Gemma 3 technical report","year":"2025"},{"key":"ref39","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","volume-title":"Stop reasoning! when multimodal llm with chain-of-thought reasoning meets adversarial image","author":"Wang","year":"2024"},{"key":"ref41","article-title":"Audio is the achilles\u2019 heel: Red teaming audio large multimodal models","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00884"},{"key":"ref43","article-title":"Gptfuzzer: Red teaming large language models with auto-generated jailbreak prompts","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","first-page":"46595","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","volume":"36","author":"Zheng","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref45","volume":"19","author":"Zou","year":"2024","journal-title":"Universal and transferable adversarial attacks on aligned language models"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,20]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373940\/11374285\/11374286.pdf?arnumber=11374286","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:32:54Z","timestamp":1771918374000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11374286\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iccvw69036.2025.00311","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}