{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T16:48:11Z","timestamp":1793206091628,"version":"4.5.0"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733468","type":"print"},{"value":"9783031733475","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73347-5_6","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T05:15:43Z","timestamp":1730092543000},"page":"93-109","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Latent Guard: A\u00a0Safety Framework for\u00a0Text-to-Image Generation"],"prefix":"10.1007","author":[{"given":"Runtao","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashkan","family":"Khakzar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jindong","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qifeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip","family":"Torr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabio","family":"Pizzati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Brack, M., Schramowski, P., Kersting, K.: Distilling adversarial prompts from safety benchmarks: Report for the adversarial nibbler challenge. In: ACL Workshops (2023)","DOI":"10.18653\/v1\/2023.artofsafety-1.3"},{"key":"6_CR2","unstructured":"Chin, Z.Y., Jiang, C.M., Huang, C.C., Chen, P.Y., Chiu, W.C.: Prompting4debugging: red-teaming text-to-image diffusion models by finding problematic prompts. In: ICML (2024)"},{"key":"6_CR3","unstructured":"Daras, G., Dimakis, A.G.: Discovering the hidden vocabulary of dalle-2. arXiv preprint arXiv:2206.00169 (2022)"},{"key":"6_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)"},{"key":"6_CR5","unstructured":"Gu, J.: Responsible generative ai: What to generate and what not. arXiv preprint arXiv:2404.05783 (2024)"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"6_CR7","unstructured":"Hammoud, H.A.A.K., Itani, H., Pizzati, F., Torr, P., Bibi, A., Ghanem, B.: Synthclip: are we ready for a fully synthetic clip training? arXiv preprint arXiv:2402.01832 (2024)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: Clipscore: a reference-free evaluation metric for image captioning. In: EMNLP (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"6_CR9","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"6_CR10","unstructured":"Inan, H., et\u00a0al.: Llama guard: Llm-based input-output safeguard for human-AI conversations. arXiv preprint arXiv:2312.06674 (2023)AI"},{"key":"6_CR11","unstructured":"Khosla, P., et al.: Supervised contrastive learning. In: NeurIPS (2020)"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Li, H., Shen, C., Torr, P., Tresp, V., Gu, J.: Self-discovering interpretable diffusion latent directions for responsible text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12006\u201312016 (2024)","DOI":"10.1109\/CVPR52733.2024.01141"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"6_CR14","unstructured":"Liu, Q., Kortylewski, A., Bai, Y., Bai, S., Yuille, A.: Discovering failure modes of text-guided diffusion models via adversarial search. In: ICLR (2024)"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Liu, X., Zhu, Y., Gu, J., Lan, Y., Yang, C., Qiao, Y.: Mm-safetybench: a benchmark for safety evaluation of multimodal large language models. arXiv preprint arXiv:2311.17600 (2023)","DOI":"10.1007\/978-3-031-72992-8_22"},{"key":"6_CR16","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"6_CR17","unstructured":"van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-sne. JMLR (2008)"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Markov, T., et al.: A holistic approach to undesired content detection in the real world. In: AAAI (2023)","DOI":"10.1609\/aaai.v37i12.26752"},{"key":"6_CR19","unstructured":"Mielke, S.J., et\u00a0al.: Between words and characters: a brief history of open-vocabulary modeling and tokenization in nlp. arXiv preprint arXiv:2112.10508 (2021)"},{"key":"6_CR20","unstructured":"Milli\u00e8re, R.: Adversarial attacks on image generation with made-up words. arXiv preprint arXiv:2208.04135 (2022)"},{"key":"6_CR21","unstructured":"Nichol, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. In: ICML (2022)"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Park, S., Moon, S., Park, S., Kim, J.: Localization and manipulation of immoral visual cues for safe text-to-image generation. In: WACV (2024)","DOI":"10.1109\/WACV57701.2024.00461"},{"key":"6_CR23","unstructured":"Podell, D., et al.: Sdxl: Improving latent diffusion models for high-resolution image synthesis. In: ICLR (2024)"},{"key":"6_CR24","unstructured":"Poppi, S., Poppi, T., Cocchi, F., Cornia, M., Baraldi, L., Cucchiara, R.: Removing nsfw concepts from vision-and-language models for text-to-image retrieval and generation. arXiv preprint arXiv:2311.16254 (2023)"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Qu, Y., Shen, X., He, X., Backes, M., Zannettou, S., Zhang, Y.: Unsafe diffusion: on the generation of unsafe images and hateful memes from text-to-image models. arXiv preprint arXiv:2305.13873 (2023)","DOI":"10.1145\/3576915.3616679"},{"key":"6_CR26","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"6_CR27","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"6_CR28","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML (2021)"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Schramowski, P., Brack, M., Deiseroth, B., Kersting, K.: Safe latent diffusion: mitigating inappropriate degeneration in diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02157"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Schramowski, P., Tauchmann, C., Kersting, K.: Can machines help us answering question 16 in datasheets, and in turn reflecting on inappropriate content? In: FAcCT, pp. 1350\u20131361 (2022)","DOI":"10.1145\/3531146.3533192"},{"key":"6_CR33","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"6_CR34","unstructured":"Wen, Y., Jain, N., Kirchenbauer, J., Goldblum, M., Geiping, J., Goldstein, T.: Hard prompts made easy: gradient-based discrete optimization for prompt tuning and discovery. In: NeurIPS (2024)"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Yang, Y., Gao, R., Wang, X., Xu, N., Xu, Q.: Mma-diffusion: multimodal attack on diffusion models. arXiv preprint arXiv:2311.17516 (2023)","DOI":"10.1109\/CVPR52733.2024.00739"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Yang, Y., Hui, B., Yuan, H., Gong, N., Cao, Y.: Sneakyprompt: jailbreaking text-to-image generative models. In: 2024 IEEE Symposium on Security and Privacy (2024)","DOI":"10.1109\/SP54263.2024.00123"},{"key":"6_CR37","unstructured":"Zhai, S., Wang, W., Li, J., Dong, Y., Su, H., Shen, Q.: Discovering universal semantic triggers for text-to-image synthesis. arXiv preprint arXiv:2402.07562 (2024)"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"6_CR39","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: Evaluating text generation with bert. In: ICLR (2020)"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Yeh, R.A.: Imma: Immunizing text-to-image models against malicious adaptation. arXiv preprint arXiv:2311.18815 (2023)","DOI":"10.1007\/978-3-031-72933-1_26"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Zhu, M., Pan, P., Chen, W., Yang, Y.: Dm-gan: dynamic memory generative adversarial networks for text-to-image synthesis. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00595"},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Zhuang, H., Zhang, Y., Liu, S.: A pilot study of query-free adversarial attack against stable diffusion. In: CVPR Workshops (2023)","DOI":"10.1109\/CVPRW59228.2023.00236"},{"key":"6_CR43","unstructured":"Website: The complete list of banned words in midjourney you need to know (2022). Link"},{"key":"6_CR44","unstructured":"Website: Diffusers: State-of-the-art diffusion models (2022). Link"},{"key":"6_CR45","unstructured":"Website: Midjourney (2022). Link"},{"key":"6_CR46","unstructured":"Website: Nudenet (2022). Link"},{"key":"6_CR47","unstructured":"Website: Dall-e 3 system card (2023). Link"},{"key":"6_CR48","unstructured":"Website: Leonardo ai content moderation filter: Everything you need to know (2023). Link"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73347-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T05:31:13Z","timestamp":1732944673000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73347-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031733468","9783031733475"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73347-5_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}