{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T14:59:34Z","timestamp":1763564374593,"version":"3.38.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-22-1-0035"],"award-info":[{"award-number":["W911NF-22-1-0035"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3539933","type":"journal-article","created":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T18:43:05Z","timestamp":1738953785000},"page":"32661-32680","source":"Crossref","is-referenced-by-count":1,"title":["A Systematic Review of Open Datasets Used in Text-to-Image (T2I) Gen AI Model Safety"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1829-566X","authenticated-orcid":false,"given":"Trupti","family":"Bavalatti","sequence":"first","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0129-2870","authenticated-orcid":false,"given":"Osama","family":"Ahmed","sequence":"additional","affiliation":[{"name":"Interdisciplinary Data Science, Duke University, Durham, NC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7496-1945","authenticated-orcid":false,"given":"Dhaval","family":"Potdar","sequence":"additional","affiliation":[{"name":"Interdisciplinary Data Science, Duke University, Durham, NC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8218-0331","authenticated-orcid":false,"given":"Rakeen","family":"Rouf","sequence":"additional","affiliation":[{"name":"Interdisciplinary Data Science, Duke University, Durham, NC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9629-4766","authenticated-orcid":false,"given":"Faraz","family":"Jawed","sequence":"additional","affiliation":[{"name":"Interdisciplinary Data Science, Duke University, Durham, NC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6381-6293","authenticated-orcid":false,"given":"Manish","family":"Kumar Govind","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of North Carolina at Charlotte, Charlotte, NC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9570-0186","authenticated-orcid":false,"given":"Siddharth","family":"Krishnan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of North Carolina at Charlotte, Charlotte, NC, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.12092"},{"key":"ref2","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"arXiv:2205.11487"},{"key":"ref3","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref4","article-title":"Large image datasets: A pyrrhic win for computer vision?","author":"Prabhu","year":"2020","journal-title":"arXiv:2006.16923"},{"volume-title":"DALL\u22c5E 2 System Card","year":"2022","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445918"},{"key":"ref7","article-title":"Ethical and social risks of harm from language models","author":"Weidinger","year":"2021","journal-title":"arXiv:2112.04359"},{"key":"ref8","article-title":"Process for adapting language models to society (PALMS) with values-targeted datasets","author":"Solaiman","year":"2021","journal-title":"arXiv:2106.10328"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"ref10","article-title":"Datasets for large language models: A comprehensive survey","author":"Liu","year":"2024","journal-title":"arXiv:2402.18041"},{"key":"ref11","article-title":"A comprehensive survey of direct preference optimization: Datasets, theories, variants, and applications","author":"Xiao","year":"2024","journal-title":"arXiv:2410.15595"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-024-3767-3"},{"key":"ref13","article-title":"A survey on multimodal benchmarks: In the era of large AI models","author":"Li","year":"2024","journal-title":"arXiv:2409.18142"},{"key":"ref14","article-title":"Inadequacies of large language model benchmarks in the era of generative artificial intelligence","author":"McIntosh","year":"2024","journal-title":"arXiv:2402.09880"},{"key":"ref15","article-title":"Gender artifacts in visual datasets","author":"Meister","year":"2022","journal-title":"arXiv:2206.09191"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_43"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3375709"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/access.2023.3306422"},{"key":"ref19","article-title":"Multimodal datasets: Misogyny, pornography, and malignant stereotypes","author":"Birhane","year":"2021","journal-title":"arXiv:2110.01963"},{"key":"ref20","article-title":"SafetyPrompts: A systematic review of open datasets for evaluating and improving large language model safety","author":"R\u00f6ttger","year":"2024","journal-title":"arXiv:2404.05399"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02157"},{"key":"ref22","first-page":"1","article-title":"Latent guard: A safety framework for text-to-image generation","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Liu"},{"key":"ref23","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"arXiv:2201.12086"},{"key":"ref24","first-page":"1","article-title":"ART: Automatic red-teaming for text-to-image models to protect benign users","volume-title":"Proc. 38th Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Li"},{"key":"ref25","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"ref26","first-page":"1","article-title":"Prompting4Debugging: Red-teaming text-to-image diffusion models by finding problematic prompts","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","author":"Chin"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00123"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658913"},{"key":"ref29","article-title":"MMA-Diffusion: MultiModal attack on diffusion models","author":"Yang","year":"2023","journal-title":"arXiv:2311.17516"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3670295"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-020-01440-1"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.447"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.06.009"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-012-0278-x"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"issue":"4","key":"ref36","first-page":"35","article-title":"Modern information retrieval: A brief overview","volume":"24","author":"Singhal","year":"2001","journal-title":"IEEE Data Eng. Bull."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07566-y"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-024-02355-z"},{"volume-title":"Unmasking AI: My Mission to Protect What Is Human in a World of Machines","year":"2023","author":"Buolamwini","key":"ref39"},{"volume-title":"TextBlob: Simplified Text Processing","year":"2014","author":"Loria","key":"ref40"},{"volume-title":"XLM-RoBERTa Base Language Detection","year":"2021","author":"Luca","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.70777\/agi.v1i1.10603"},{"volume-title":"Regulatory Framework on AI | Shaping Europe\u2019s Digital Future","year":"2024","key":"ref43"},{"volume-title":"Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence","year":"2023","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.2307\/2685469"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-010-0175-9"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00230"},{"key":"ref48","article-title":"#InsTag: Instruction tagging for analyzing supervised fine-tuning of large language models","author":"Lu","year":"2023","journal-title":"arXiv:2308.07074"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1201\/b16018"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6287639\/10820123\/10877814-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10877814.pdf?arnumber=10877814","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,25]],"date-time":"2025-02-25T05:25:08Z","timestamp":1740461108000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10877814\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3539933","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}