{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:43:11Z","timestamp":1763192591029,"version":"3.45.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228287","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Unaligning Everything: Or Aligning Any Text to Any Image in Multimodal Models"],"prefix":"10.1109","author":[{"given":"Shaeke","family":"Salman","sequence":"first","affiliation":[{"name":"Florida State University,Department of Computer Science,Tallahassee,Florida"}]},{"given":"Montasir","family":"Shams","sequence":"additional","affiliation":[{"name":"Florida State University,Department of Computer Science,Tallahassee,Florida"}]},{"given":"Mao","family":"Nishino","sequence":"additional","affiliation":[{"name":"Florida State University,Department of Mathematics,Tallahassee,Florida"}]},{"given":"Xiuwen","family":"Liu","sequence":"additional","affiliation":[{"name":"Florida State University,Department of Computer Science,Tallahassee,Florida"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2022","journal-title":"CoRR"},{"year":"2023","key":"ref2","article-title":"Gpt-4 technical report"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000198"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4335905"},{"key":"ref6","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","key":"ref7"},{"key":"ref8","first-page":"4171","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"Proceedings of NAACL-HLT 2019","author":"Devlin"},{"key":"ref9","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","volume":"139","author":"Radford"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802618"},{"article-title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","year":"2022","author":"Shah","key":"ref11"},{"article-title":"Explaining and harnessing adversarial examples","volume-title":"International Conference on Learning Representations","author":"Goodfellow","key":"ref12"},{"key":"ref13","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2014","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12028"},{"article-title":"Universal and transferable adversarial attacks on aligned language models","year":"2023","author":"Zou","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"article-title":"Intriguing equivalence structures of the embedding space of vision transformers","year":"2024","author":"Salman","key":"ref17"},{"article-title":"Language models are few-shot learners","year":"2020","author":"Brown","key":"ref18"},{"article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","year":"2023","author":"Zhu","key":"ref19"},{"key":"ref20","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref21"},{"article-title":"Visual instruction tuning","year":"2023","author":"Liu","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"article-title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","year":"2020","author":"Croce","key":"ref24"},{"key":"ref25","article-title":"Are aligned neural networks adversarially aligned?","author":"Carlini","year":"2023","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30150"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3663530.3665021"},{"article-title":"Jailbroken: How does llm safety training fail?","year":"2023","author":"Wei","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01007"},{"article-title":"On the adversarial robustness of vision transformers","volume-title":"ML Safety Workshop, 36th Conference on Neural Information Processing Systems (NeurIPS 2022)","author":"Shao","key":"ref30"},{"article-title":"What do we learn from inverting clip models?","year":"2024","author":"Kazemi","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"Automatically auditing large language models via discrete optimization","year":"2023","author":"Jones","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3308560.3317593"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5105"},{"article-title":"Openclip","year":"2021","author":"Ilharco","key":"ref36"},{"article-title":"Intriguing differences between zero-shot and systematic evaluations of vision-language transformer models","year":"2024","author":"Salman","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/591"},{"article-title":"Understanding zero-shot adversarial robustness for large-scale models","year":"2023","author":"Mao","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00260"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228287.pdf?arnumber=11228287","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:39:12Z","timestamp":1763192352000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228287\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228287","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}