{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:19Z","timestamp":1777865359993,"version":"3.51.4"},"reference-count":44,"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"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Singapore","doi-asserted-by":"publisher","award":["AISG2-PhD-2021-08-023[T]"],"award-info":[{"award-number":["AISG2-PhD-2021-08-023[T]"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202340,72474159"],"award-info":[{"award-number":["62202340,72474159"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2042025kf0054"],"award-info":[{"award-number":["2042025kf0054"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2025AFB455"],"award-info":[{"award-number":["2025AFB455"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01726","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18575-18584","source":"Crossref","is-referenced-by-count":0,"title":["Automated Red Teaming for Text-to-Image Models Through Feedback-Guided Prompt Iteration with Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Wei","family":"Xu","sequence":"first","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kangjie","family":"Chen","sequence":"additional","affiliation":[{"name":"Digital Trust Centre, Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Run","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Information Management, Wuhan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lina","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"4chan"},{"key":"ref2","volume-title":"Lexica"},{"key":"ref3","volume-title":"Meta-llama-guard-2-8b"},{"key":"ref4","volume-title":"LLaVA-1.6-Mistral-7B"},{"key":"ref5","volume-title":"NSFW image detection"},{"key":"ref6","volume-title":"Stable diffusion safety filter"},{"key":"ref7","volume-title":"Llama-3.3-70B-Instruct","year":"2024"},{"key":"ref8","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594095"},{"key":"ref11","article-title":"BlackForestLabs","volume-title":"FLUX.1","year":"2024"},{"key":"ref12","article-title":"Toward trustworthy ai development: mechanisms for supporting verifiable claims","author":"Brundage","year":"2020","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Generative ai and creative work: Narratives, values, and impacts","author":"Caramiaux","year":"2025","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00230"},{"key":"ref15","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"2","key":"ref16","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i25.34821"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3571946"},{"key":"ref19","article-title":"Art: Automatic red-teaming for text-to-image models to protect benign users","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref21","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Groot: Adversarial testing for generative text-to-image models with tree-based semantic transformation","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Flirt: Feedback loop in-context red teaming","author":"Mehrabi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Midjourney","volume-title":"Midjourney","year":"2023"},{"key":"ref25","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604711"},{"key":"ref27","volume-title":"DALL.E 3","year":"2023"},{"key":"ref28","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Podell","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3616679"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658913"},{"key":"ref31","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533192"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02157"},{"key":"ref36","article-title":"Stability AI","volume-title":"DeepFloyd IF","year":"2023"},{"key":"ref37","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00739"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00123"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref43","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210080"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444110.pdf?arnumber=11444110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:20:38Z","timestamp":1777530038000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01726","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}