{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:21:06Z","timestamp":1765340466510,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754928","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:47:18Z","timestamp":1761374838000},"page":"11279-11287","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Universally Unfiltered and Unseen: Input-Agnostic Multimodal Jailbreaks against Text-to-Image Model Safeguards"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5704-2486","authenticated-orcid":false,"given":"Song","family":"Yan","sequence":"first","affiliation":[{"name":"Information Engineering University, Zhengzhou, Henan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2144-2065","authenticated-orcid":false,"given":"Hui","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, Hubei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8499-9402","authenticated-orcid":false,"given":"Jinlong","family":"Fei","sequence":"additional","affiliation":[{"name":"Information Engineering University, Zhengzhou, Henan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7624-6442","authenticated-orcid":false,"given":"Guoliang","family":"Yang","sequence":"additional","affiliation":[{"name":"Information Engineering University, Zhengzhou, Henan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0745-4294","authenticated-orcid":false,"given":"Zhengyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, Shanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3846-9157","authenticated-orcid":false,"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, Hubei, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"284","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan","author":"Athalye Anish","year":"2018","unstructured":"Anish Athalye, Logan Engstrom, Andrew Ilyas, and Kevin Kwok. 2018. Synthesizing Robust Adversarial Examples. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10-15, 2018 (Proceedings of Machine Learning Research, Vol. 80), Jennifer G. Dy and Andreas Krause (Eds.). PMLR, 284-293."},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 1-11","author":"Brown Trevor","key":"e_1_3_2_1_2_1","unstructured":"Trevor Brown, Daniel A. Engelmann, and Sebastian A. Grunewald. 2017. Adversarial patches. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 1-11."},{"key":"e_1_3_2_1_3_1","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024","author":"Chin Zhi-Yi","year":"2024","unstructured":"Zhi-Yi Chin, Chieh-Ming Jiang, Ching-Chun Huang, Pin-Yu Chen, and Wei-Chen Chiu. 2024. Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net."},{"key":"e_1_3_2_1_4_1","unstructured":"CompVis. 2024. Model Card for stable-diffusion-safety-checker. https:\/\/huggingface.co\/CompVis\/stable-diffusion-safety-checker. Accessed: 2024-09-6."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00230"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02322"},{"key":"e_1_3_2_1_7_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Hou Bairu","year":"2023","unstructured":"Bairu Hou, Jinghan Jia, Yihua Zhang, Guanhua Zhang, Yang Zhang, Sijia Liu, and Shiyu Chang. 2023. TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net."},{"key":"e_1_3_2_1_8_1","volume-title":"Perception-guided jailbreak against text-to-image models. arXiv preprint arXiv:2408.10848","author":"Huang Yihao","year":"2024","unstructured":"Yihao Huang, Le Liang, Tianlin Li, Xiaojun Jia, Run Wang, Weikai Miao, Geguang Pu, and Yang Liu. 2024. Perception-guided jailbreak against text-to-image models. arXiv preprint arXiv:2408.10848 (2024)."},{"key":"e_1_3_2_1_9_1","first-page":"22634","volume-title":"Ablating Concepts in Text-to-Image Diffusion Models. In IEEE\/CVF International Conference on Computer Vision, ICCV 2023","author":"Kumari Nupur","year":"2023","unstructured":"Nupur Kumari, Bingliang Zhang, Sheng-Yu Wang, Eli Shechtman, Richard Zhang, and Jun-Yan Zhu. 2023. Ablating Concepts in Text-to-Image Diffusion Models. In IEEE\/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023. IEEE, 22634-22645."},{"key":"e_1_3_2_1_10_1","unstructured":"Leonardo.AI. 2023. Leonardo.AI. https:\/\/leonardo.ai\/ Accessed: 2024-09-15."},{"key":"e_1_3_2_1_11_1","first-page":"4711","volume-title":"33rd USENIX Security Symposium (USENIX Security 24)","author":"Liu Tong","year":"2024","unstructured":"Tong Liu, Zhe Zhao, Yinpeng Dong, Guozhu Meng, and Kai Chen. 2024. Making them ask and answer: Jailbreaking large language models in few queries via disguise and reconstruction. In 33rd USENIX Security Symposium (USENIX Security 24). 4711-4728."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.02928"},{"key":"e_1_3_2_1_13_1","volume-title":"Flirt: Feedback loop in-context red teaming. arXiv preprint arXiv:2308.04265","author":"Mehrabi Ninareh","year":"2023","unstructured":"Ninareh Mehrabi, Palash Goyal, Christophe Dupuy, Qian Hu, Shalini Ghosh, Richard Zemel, Kai-Wei Chang, Aram Galstyan, and Rahul Gupta. 2023. Flirt: Feedback loop in-context red teaming. arXiv preprint arXiv:2308.04265 (2023)."},{"key":"e_1_3_2_1_14_1","unstructured":"OpenAI. 2025. DALL\u00b7E 3. https:\/\/openai.com\/index\/dall-e-3\/. Accessed: 2025-07-17."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3616679"},{"key":"e_1_3_2_1_16_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_18_1","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022b. Stable Diffusion - v1.5. https:\/\/huggingface.co\/runwayml\/stable-diffusion-v1-5. Accessed: 2024-08-18."},{"key":"e_1_3_2_1_19_1","unstructured":"Runway Inc. 2023. Runway. https:\/\/runwayml.com\/ Accessed: 2024-09-5."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02157"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533192"},{"key":"e_1_3_2_1_22_1","unstructured":"Christoph Schuhmann Richard Beaumont Radu Vencu Cade Gordon Ross Wightman Mehdi Cherti Tharindu Coombes Alex Katta Luis Villalba and Marco Patacchiola. 2022. LAION-5B: An open large-scale dataset for training next generation image-text models. https:\/\/laion.ai\/blog\/laion-5b\/. Accessed: 2024-09-18."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"e_1_3_2_1_24_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Tsai Yu-Lin","year":"2024","unstructured":"Yu-Lin Tsai, Chia-Yi Hsu, Chulin Xie, Chih-Hsun Lin, Jia-You Chen, Bo Li, Pin-Yu Chen, Chia-Mu Yu, and Chun-Ying Huang. 2024. Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17648"},{"key":"e_1_3_2_1_26_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wei Alexander","year":"2024","unstructured":"Alexander Wei, Nika Haghtalab, and Jacob Steinhardt. 2024. Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26777"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00739"},{"key":"e_1_3_2_1_29_1","volume-title":"Guardt2i: Defending text-to-image models from adversarial prompts. arXiv preprint arXiv:2403.01446","author":"Yang Yijun","year":"2024","unstructured":"Yijun Yang, Ruiyuan Gao, Xiao Yang, Jianyuan Zhong, and Qiang Xu. 2024b. Guardt2i: Defending text-to-image models from adversarial prompts. arXiv preprint arXiv:2403.01446 (2024)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00123"},{"key":"e_1_3_2_1_31_1","volume-title":"32nd USENIX Security Symposium, USENIX Security 2023","author":"Zhang Shibo","year":"2023","unstructured":"Shibo Zhang, Yushi Cheng, Wenjun Zhu, Xiaoyu Ji, and Wenyuan Xu. 2023a. CAPatch: Physical Adversarial Patch against Image Captioning Systems. In 32nd USENIX Security Symposium, USENIX Security 2023, Anaheim, CA, USA, August 9-11, 2023, Joseph A. Calandrino and Carmela Troncoso (Eds.). USENIX Association, 679-696."},{"key":"e_1_3_2_1_32_1","first-page":"36748","article-title":"Defensive unlearning with adversarial training for robust concept erasure in diffusion models","volume":"37","author":"Zhang Yimeng","year":"2024","unstructured":"Yimeng Zhang, Xin Chen, Jinghan Jia, Yihua Zhang, Chongyu Fan, Jiancheng Liu, Mingyi Hong, Ke Ding, and Sijia Liu. 2024. Defensive unlearning with adversarial training for robust concept erasure in diffusion models. Advances in Neural Information Processing Systems, Vol. 37 (2024), 36748-36776.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.11868"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01738"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00236"},{"key":"e_1_3_2_1_36_1","volume-title":"Universal and transferable adversarial attacks on aligned language models. arXiv preprint arXiv:2307.15043","author":"Zou Andy","year":"2023","unstructured":"Andy Zou, Zifan Wang, J Zico Kolter, and Matt Fredrikson. 2023. Universal and transferable adversarial attacks on aligned language models. arXiv preprint arXiv:2307.15043 (2023)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:18:36Z","timestamp":1765340316000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754928"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":36,"alternative-id":["10.1145\/3746027.3754928","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754928","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}