{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T22:16:54Z","timestamp":1766441814815,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","funder":[{"name":"the Natural Science Foundation of China","award":["62372423, 62121002, 62072421"],"award-info":[{"award-number":["62372423, 62121002, 62072421"]}]},{"name":"the National Research Foundation, Singapore under its National Large Language Models Funding Initiative","award":["AISG-NMLP-2024-004"],"award-info":[{"award-number":["AISG-NMLP-2024-004"]}]},{"name":"the National Research Foundation, Singapore under its AI Singapore Programme","award":["AISG4-GC-2023-008-1B"],"award-info":[{"award-number":["AISG4-GC-2023-008-1B"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,19]]},"DOI":"10.1145\/3719027.3744835","type":"proceedings-article","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T23:32:38Z","timestamp":1763854358000},"page":"2818-2832","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4580-539X","authenticated-orcid":false,"given":"Peigui","family":"Qi","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5690-2364","authenticated-orcid":false,"given":"Kunsheng","family":"Tang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4703-4641","authenticated-orcid":false,"given":"Wenbo","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5576-6108","authenticated-orcid":false,"given":"Weiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4417-9316","authenticated-orcid":false,"given":"Nenghai","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6595-6650","authenticated-orcid":false,"given":"Tianwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0974-9299","authenticated-orcid":false,"given":"Qing","family":"Guo","sequence":"additional","affiliation":[{"name":"CFAR and IHPC, A*STAR, Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4230-1077","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"CFAR and IHPC, A*STAR, Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Stable Diffusion V2.1. https:\/\/huggingface.co\/stabilityai\/stable-diffusion-2-1 Retrieved","author":"Stability AI.","year":"2024","unstructured":"Stability AI. 2022. Stable Diffusion V2.1. https:\/\/huggingface.co\/stabilityai\/stable-diffusion-2-1 Retrieved November 17, 2024 from"},{"key":"e_1_3_2_1_2_1","volume-title":"https:\/\/docs.aws.amazon.com\/comprehend\/latest\/dg\/what-is.html Retrieved","author":"Comprehend Amazon","year":"2024","unstructured":"Amazon. 2023. Amazon Comprehend. https:\/\/docs.aws.amazon.com\/comprehend\/latest\/dg\/what-is.html Retrieved November 17, 2024 from"},{"key":"e_1_3_2_1_3_1","volume-title":"33rd USENIX Security Symposium, USENIX Security","author":"An Shengwei","year":"2024","unstructured":"Shengwei An, Lu Yan, and Siyuan Cheng at el., 2024. Rethinking the Invisible Protection against Unauthorized Image Usage in Stable Diffusion. In 33rd USENIX Security Symposium, USENIX Security 2024. USENIX Association."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3690346"},{"key":"e_1_3_2_1_5_1","volume-title":"Forty-first International Conference on Machine Learning, ICML","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."},{"key":"e_1_3_2_1_6_1","volume-title":"Directly Fine-Tuning Diffusion Models on Differentiable Rewards. In The Twelfth International Conference on Learning Representations, ICLR","author":"Clark Kevin","year":"2024","unstructured":"Kevin Clark, Paul Vicol, Kevin Swersky, and David J. Fleet. 2024. Directly Fine-Tuning Diffusion Models on Differentiable Rewards. In The Twelfth International Conference on Learning Representations, ICLR 2024."},{"volume-title":"Stable Diffusion V1.4. https:\/\/huggingface.co\/CompVis\/stable-diffusion-v-1-4-original Retrieved","year":"2024","key":"e_1_3_2_1_7_1","unstructured":"CompVis. 2022. Stable Diffusion V1.4. https:\/\/huggingface.co\/CompVis\/stable-diffusion-v-1-4-original Retrieved November 17, 2024 from"},{"volume-title":"Stable Diffusion Safety Checker. https:\/\/huggingface.co\/CompVis\/stable-diffusion-safety-checker Retrieved","year":"2024","key":"e_1_3_2_1_8_1","unstructured":"CompVis. 2023. Stable Diffusion Safety Checker. https:\/\/huggingface.co\/CompVis\/stable-diffusion-safety-checker Retrieved November 17, 2024 from"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3690205"},{"key":"e_1_3_2_1_10_1","first-page":"1196","volume-title":"Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security, CCS 2024","author":"Kunsheng","year":"2024","unstructured":"Kunsheng Tang et al., 2024. GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models. In Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security, CCS 2024, Salt Lake City, UT, USA, October 14-18, 2024. ACM, 1196-1210."},{"key":"e_1_3_2_1_11_1","volume-title":"How AI is being abused to create child sexual abuse imagery. https:\/\/www.iwf.org.uk\/media\/q4zll2ya\/iwf-ai-csam-report_public-oct23v1.pdf Retrieved","author":"Foundation Internet Watch","year":"2024","unstructured":"Internet Watch Foundation. 2023. How AI is being abused to create child sexual abuse imagery. https:\/\/www.iwf.org.uk\/media\/q4zll2ya\/iwf-ai-csam-report_public-oct23v1.pdf Retrieved December 4, 2024 from"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00230"},{"key":"e_1_3_2_1_13_1","volume-title":"Unstable Diffusion: Ethical challenges and some ways forward. https:\/\/montrealethics.ai\/unstable-diffusion-ethical-challenges-and-some-ways-forward\/ Retrieved","author":"Gupta Abhishek","year":"2022","unstructured":"Abhishek Gupta. 2022. Unstable Diffusion: Ethical challenges and some ways forward. https:\/\/montrealethics.ai\/unstable-diffusion-ethical-challenges-and-some-ways-forward\/ Retrieved December 4, 2024 from"},{"key":"e_1_3_2_1_14_1","volume-title":"Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020."},{"key":"e_1_3_2_1_15_1","volume-title":"Classifier-Free Diffusion Guidance. CoRR","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-Free Diffusion Guidance. CoRR, Vol. abs\/2207.12598 (2022). arXiv:2207.12598"},{"key":"e_1_3_2_1_16_1","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Huang Kaiyi","year":"2023","unstructured":"Kaiyi Huang, Kaiyue Sun, Enze Xie, Zhenguo Li, and Xihui Liu. 2023. T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023."},{"key":"e_1_3_2_1_17_1","volume-title":"https:\/\/huggingface.co\/black-forest-labs\/FLUX.1-dev Retrieved","author":"Labs Black Forest","year":"2024","unstructured":"Black Forest Labs. 2024. FLUX.1. https:\/\/huggingface.co\/black-forest-labs\/FLUX.1-dev Retrieved November 17, 2024 from"},{"key":"e_1_3_2_1_18_1","volume-title":"Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024","author":"Li Guanlin","year":"2024","unstructured":"Guanlin Li, Kangjie Chen, Shudong Zhang, Jie Zhang, and Tianwei Zhang. 2024a. ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3670295"},{"key":"e_1_3_2_1_20_1","volume-title":"Zurich, Switzerland","volume":"755","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, and Serge J. Belongie at al., 2014. Microsoft COCO: Common Objects in Context. In Computer Vision - ECCV 2014 - 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V (Lecture Notes in Computer Science, Vol. 8693). Springer, 740-755."},{"key":"e_1_3_2_1_21_1","first-page":"4461","volume-title":"Influence Patterns for Explaining Information Flow in BERT. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Lu Kaiji","year":"2021","unstructured":"Kaiji Lu, Zifan Wang, Piotr Mardziel, and Anupam Datta. 2021. Influence Patterns for Explaining Information Flow in BERT. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021. 4461-4474."},{"key":"e_1_3_2_1_22_1","volume-title":"Stable Bias: Evaluating Societal Representations in Diffusion Models. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Luccioni Sasha","year":"2023","unstructured":"Sasha Luccioni, Christopher Akiki, Margaret Mitchell, and Yacine Jernite. 2023. Stable Bias: Evaluating Societal Representations in Diffusion Models. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023."},{"volume-title":"NSFW Text Classifier. https:\/\/huggingface.co\/michellejieli\/NSFW_text_classifier Retrieved","year":"2024","key":"e_1_3_2_1_23_1","unstructured":"Michellejieli. 2023. NSFW Text Classifier. https:\/\/huggingface.co\/michellejieli\/NSFW_text_classifier Retrieved November 17, 2024 from"},{"key":"e_1_3_2_1_24_1","volume-title":"https:\/\/learn.microsoft.com\/en-us\/azure\/ai-services\/content-moderator\/overview Retrieved","author":"Moderator Azure","year":"2024","unstructured":"Microsoft. 2024. Azure Moderator. https:\/\/learn.microsoft.com\/en-us\/azure\/ai-services\/content-moderator\/overview Retrieved November 17, 2024 from"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.61"},{"key":"e_1_3_2_1_26_1","volume-title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning, ICML 2022","volume":"16804","author":"Nichol Alexander Quinn","year":"2022","unstructured":"Alexander Quinn Nichol, Prafulla Dhariwal, and Aditya Ramesh et al., 2022. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162). PMLR, 16784-16804."},{"key":"e_1_3_2_1_27_1","volume-title":"https:\/\/github.com\/notAI-tech\/NudeNet Retrieved","author":"NudeNet AI","year":"2024","unstructured":"notAI tech. 2024. NudeNet. https:\/\/github.com\/notAI-tech\/NudeNet Retrieved November 17, 2024 from"},{"key":"e_1_3_2_1_28_1","volume-title":"https:\/\/platform.openai.com\/docs\/guides\/moderation\/overview\/ Retrieved","author":"Moderation Overview AI.","year":"2024","unstructured":"OpenAI. 2023. Moderation Overview. https:\/\/platform.openai.com\/docs\/guides\/moderation\/overview\/ Retrieved November 17, 2024 from"},{"key":"e_1_3_2_1_29_1","volume-title":"Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems","author":"Peng Shengyun","year":"2024","unstructured":"Shengyun Peng, Pin-Yu Chen, Matthew Hull, and Duen Horng Chau. 2024. Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3616679"},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021 (Proceedings of Machine Learning Research","volume":"8763","author":"Radford Alec","unstructured":"Alec Radford, Jong Wook Kim, and Chris Hallacy at al., 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021 (Proceedings of Machine Learning Research, Vol. 139). PMLR, 8748-8763."},{"key":"e_1_3_2_1_32_1","unstructured":"Javier Rando Daniel Paleka and David Lindner et al. 2022. Red-Teaming the Stable Diffusion Safety Filter. CoRR Vol. abs\/2210.04610 (2022)."},{"key":"e_1_3_2_1_33_1","first-page":"10674","volume-title":"High-Resolution Image Synthesis with Latent Diffusion Models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR","author":"Rombach Robin","year":"2022","unstructured":"Robin Rombach, Andreas Blattmann, and Dominik Lorenz et al., 2022. High-Resolution Image Synthesis with Latent Diffusion Models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022. IEEE, 10674-10685."},{"key":"e_1_3_2_1_34_1","first-page":"22522","volume-title":"Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR","author":"Schramowski Patrick","year":"2023","unstructured":"Patrick Schramowski, Manuel Brack, Bj\u00f6rn Deiseroth, and Kristian Kersting. 2023. Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023. IEEE, 22522-22531."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533192"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3690297"},{"key":"e_1_3_2_1_37_1","volume-title":"32nd USENIX Security Symposium, USENIX Security","author":"Shan Shawn","year":"2023","unstructured":"Shawn Shan, Jenna Cryan, and Emily Wenger at al., 2023. Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models. In 32nd USENIX Security Symposium, USENIX Security 2023. USENIX Association."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_2_1_39_1","volume-title":"Prompt Stealing Attacks Against Text-to-Image Generation Models. In 33rd USENIX Security Symposium, USENIX Security","author":"Shen Xinyue","year":"2024","unstructured":"Xinyue Shen, Yiting Qu, Michael Backes, and Yang Zhang. 2024. Prompt Stealing Attacks Against Text-to-Image Generation Models. In 33rd USENIX Security Symposium, USENIX Security 2024. USENIX Association."},{"key":"e_1_3_2_1_40_1","volume-title":"Denoising Diffusion Implicit Models. CoRR","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising Diffusion Implicit Models. CoRR, Vol. abs\/2010.02502 (2020). arXiv:2010.02502"},{"key":"e_1_3_2_1_41_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR","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."},{"key":"e_1_3_2_1_42_1","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017. 5998-6008."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.609"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3690327"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3690288"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-0487-3"},{"key":"e_1_3_2_1_47_1","volume-title":"Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024","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. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024."},{"key":"e_1_3_2_1_48_1","first-page":"897","volume-title":"SneakyPrompt: Jailbreaking Text-to-image Generative Models. In IEEE Symposium on Security and Privacy, SP","author":"Yang Yuchen","year":"2024","unstructured":"Yuchen Yang, Bo Hui, Haolin Yuan, Neil Gong, and Yinzhi Cao. 2024c. SneakyPrompt: Jailbreaking Text-to-image Generative Models. In IEEE Symposium on Security and Privacy, SP 2024. IEEE, 897-912."},{"key":"e_1_3_2_1_49_1","volume-title":"Wenbo Guo, Han Liu, and Xinyu Xing.","author":"Yu Jiahao","year":"2024","unstructured":"Jiahao Yu, Haozheng Luo, Jerry Yao-Chieh Hu, Wenbo Guo, Han Liu, and Xinyu Xing. 2024. Enhancing Jailbreak Attack Against Large Language Models through Silent Tokens. CoRR, Vol. abs\/2405.20653 (2024). arXiv:2405.20653"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"}],"event":{"name":"CCS '25: ACM SIGSAC Conference on Computer and Communications Security","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"],"location":"Taipei Taiwan","acronym":"CCS '25"},"container-title":["Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3719027.3744835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T22:12:07Z","timestamp":1766441527000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3719027.3744835"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,19]]},"references-count":50,"alternative-id":["10.1145\/3719027.3744835","10.1145\/3719027"],"URL":"https:\/\/doi.org\/10.1145\/3719027.3744835","relation":{},"subject":[],"published":{"date-parts":[[2025,11,19]]},"assertion":[{"value":"2025-11-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}