{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T19:16:31Z","timestamp":1762110991407,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031728549"},{"type":"electronic","value":"9783031728556"}],"license":[{"start":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T00:00:00Z","timestamp":1731110400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T00:00:00Z","timestamp":1731110400000},"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\/978-3-031-72855-6_8","type":"book-chapter","created":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T18:48:05Z","timestamp":1731091685000},"page":"128-145","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Safeguard Text-to-Image Diffusion Models with\u00a0Human Feedback Inversion"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9163-168X","authenticated-orcid":false,"given":"Sanghyun","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2703-6456","authenticated-orcid":false,"given":"Seohyeon","family":"Jung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1664-0799","authenticated-orcid":false,"given":"Balhae","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1566-2731","authenticated-orcid":false,"given":"Moonseok","family":"Choi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4313-4669","authenticated-orcid":false,"given":"Jinwoo","family":"Shin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6725-6874","authenticated-orcid":false,"given":"Juho","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,9]]},"reference":[{"key":"8_CR1","unstructured":"Baio, A.: Exploring 12 million of the 2.3 billion images used to train stable diffusion\u2019s image generator (2022). https:\/\/waxy.org\/2022\/08\/exploring-12-million-of-the-images-used-to-train-stable-diffusions-image-generator\/"},{"key":"8_CR2","unstructured":"Black, K., Janner, M., Du, Y., Kostrikov, I., Levine, S.: Training diffusion models with reinforcement learning. arXiv preprint arXiv:2305.13301 (2023)"},{"key":"8_CR3","unstructured":"Brack, M., Friedrich, F., Hintersdorf, D., Struppek, L., Schramowski, P., Kersting, K.: SEGA: instructing diffusion using semantic dimensions. arXiv preprint arXiv:2301.12247 (2023)"},{"key":"8_CR4","unstructured":"Brack, M., Schramowski, P., Friedrich, F., Hintersdorf, D., Kersting, K.: The stable artist: steering semantics in diffusion latent space. arXiv preprint arXiv:2212.06013 (2022)"},{"issue":"3\/4","key":"8_CR5","doi-asserted-by":"publisher","first-page":"324","DOI":"10.2307\/2334029","volume":"39","author":"RA Bradley","year":"1952","unstructured":"Bradley, R.A., Terry, M.E.: Rank analysis of incomplete block designs: I. The method of paired comparisons. Biometrika 39(3\/4), 324\u2013345 (1952)","journal-title":"Biometrika"},{"key":"8_CR6","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"8_CR8","unstructured":"Christiano, P.F., Leike, J., Brown, T., Martic, M., Legg, S., Amodei, D.: Deep reinforcement learning from human preferences. Adv. Neural. Inf. Process. Syst. 30 (2017)"},{"key":"8_CR9","first-page":"6637","volume":"33","author":"Y Du","year":"2020","unstructured":"Du, Y., Li, S., Mordatch, I.: Compositional visual generation with energy based models. Adv. Neural. Inf. Process. Syst. 33, 6637\u20136647 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR10","unstructured":"Fan, Y., et al.: DPOK: reinforcement learning for fine-tuning text-to-image diffusion models. arXiv preprint arXiv:2305.16381 (2023)"},{"issue":"5","key":"8_CR11","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1037\/h0031619","volume":"76","author":"JL Fleiss","year":"1971","unstructured":"Fleiss, J.L.: Measuring nominal scale agreement among many raters. Psychol. Bull. 76(5), 378 (1971)","journal-title":"Psychol. Bull."},{"key":"8_CR12","doi-asserted-by":"publisher","unstructured":"Gal, R., et al.: An image is worth one word: Personalizing text-to-image generation using textual inversion (2022). https:\/\/doi.org\/10.48550\/ARXIV.2208.01618, https:\/\/arxiv.org\/abs\/2208.01618","DOI":"10.48550\/ARXIV.2208.01618"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Gandikota, R., Materzynska, J., Fiotto-Kaufman, J., Bau, D.: Erasing concepts from diffusion models. arXiv preprint arXiv:2303.07345 (2023)","DOI":"10.1109\/ICCV51070.2023.00230"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Gandikota, R., Orgad, H., Belinkov, Y., Materzy\u0144ska, J., Bau, D.: Unified concept editing in diffusion models. arXiv preprint arXiv:2308.14761 (2023)","DOI":"10.1109\/WACV57701.2024.00503"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Gao, J., Galley, M., Li, L.: Neural approaches to conversational AI. In: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 1371\u20131374 (2018)","DOI":"10.1145\/3209978.3210183"},{"key":"8_CR16","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"8_CR17","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. arXiv preprint arxiv:2006.11239 (2020)"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Wang, S.Y., Shechtman, E., Zhang, R., Zhu, J.Y.: Ablating concepts in text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22691\u201322702 (2023)","DOI":"10.1109\/ICCV51070.2023.02074"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., Zhu, J.Y.: Multi-concept customization of text-to-image diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1931\u20131941 (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"8_CR20","unstructured":"Lee, K., et al.: Aligning text-to-image models using human feedback. arXiv preprint arXiv:2302.12192 (2023)"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Li, J., Monroe, W., Ritter, A., Galley, M., Gao, J., Jurafsky, D.: Deep reinforcement learning for dialogue generation. arXiv preprint arXiv:1606.01541 (2016)","DOI":"10.18653\/v1\/D16-1127"},{"key":"8_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part V. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Ni, Z., Wei, L., Li, J., Tang, S., Zhuang, Y., Tian, Q.: Degeneration-tuning: using scrambled grid shield unwanted concepts from stable diffusion. arXiv preprint arXiv:2308.02552 (2023)","DOI":"10.1145\/3581783.3611867"},{"key":"8_CR24","unstructured":"O\u2019Connor, R.: Stable diffusion 1 vs 2 - what you need to know (2022). https:\/\/www.assemblyai.com\/blog\/stable-diffusion-1-vs-2-what-you-need-to-know\/"},{"key":"8_CR25","unstructured":"OpenAI: ChatGPT (2023). https:\/\/www.openai.com\/"},{"key":"8_CR26","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Parmar, G., Zhang, R., Zhu, J.Y.: On aliased resizing and surprising subtleties in GAN evaluation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"8_CR28","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"8_CR29","unstructured":"Praneeth, B.: NudeNet: neural nets for nudity classification, detection and selective censoring (2021). https:\/\/github.com\/notAI-tech\/NudeNet"},{"key":"8_CR30","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"8_CR31","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.061251(2), 3 (2022)"},{"key":"8_CR32","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"8_CR33","unstructured":"Rando, J., Paleka, D., Lindner, D., Heim, L., Tram\u00e8r, F.: Red-teaming the stable diffusion safety filter. arXiv preprint arXiv:2210.04610 (2022)"},{"key":"8_CR34","unstructured":"Randolph, J.J.: Free-marginal multirater kappa (multirater k [free]): an alternative to Fleiss\u2019 fixed-marginal multirater kappa. Online submission (2005)"},{"issue":"1","key":"8_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3544777","volume":"42","author":"D Roich","year":"2022","unstructured":"Roich, D., Mokady, R., Bermano, A.H., Cohen-Or, D.: Pivotal tuning for latent-based editing of real images. ACM Trans. Graph. (TOG) 42(1), 1\u201313 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"8_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"8_CR39","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Schramowski, P., Brack, M., Deiseroth, B., Kersting, K.: Safe latent diffusion: mitigating inappropriate degeneration in diffusion models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.02157"},{"key":"8_CR41","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: 2022 ACM Conference on Fairness, Accountability, and Transparency, pp. 1350\u20131361 (2022)","DOI":"10.1145\/3531146.3533192"},{"key":"8_CR42","unstructured":"Schuhmann, C., et\u00a0al.: LAION-5B: an open large-scale dataset for training next generation image-text models. arXiv preprint arXiv:2210.08402 (2022)"},{"key":"8_CR43","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"8_CR44","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: Proceedings of the 32nd International Conference on Machine Learning (2015)"},{"key":"8_CR45","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"8_CR46","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"8_CR47","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"8_CR48","unstructured":"Stability AI: Stable diffusion 2.0 release (2022). https:\/\/stability.ai\/blog\/stable-diffusion-v2-release"},{"key":"8_CR49","unstructured":"Stiennon, N., et al.: Learning to summarize with human feedback. Adv. Neural. Inf. Process. Syst. 33, 3008\u20133021 (2020)"},{"key":"8_CR50","unstructured":"Thiel, D.: Identifying and eliminating CSAM in generative ml training data and models. Technical report, Stanford University, Palo Alto, CA(2023). https:\/\/purl.stanford\u00a0$$\\ldots $$"},{"key":"8_CR51","unstructured":"Yang, Z., Yi, X., Li, P., Liu, Y., Xie, X.: Unified detoxifying and debiasing in language generation via inference-time adaptive optimization. arXiv preprint arXiv:2210.04492 (2022)"},{"key":"8_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, E., Wang, K., Xu, X., Wang, Z., Shi, H.: Forget-me-not: learning to forget in text-to-image diffusion models. arXiv preprint arXiv:2211.08332 (2023)","DOI":"10.1109\/CVPRW63382.2024.00182"},{"key":"8_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, L., Song, J., Gao, A., Chen, J., Bao, C., Ma, K.: Be your own teacher: improve the performance of convolutional neural networks via self distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3713\u20133722 (2019)","DOI":"10.1109\/ICCV.2019.00381"},{"key":"8_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"}],"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\/978-3-031-72855-6_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T19:04:50Z","timestamp":1731092690000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72855-6_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,9]]},"ISBN":["9783031728549","9783031728556"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72855-6_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,9]]},"assertion":[{"value":"9 November 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"}}]}}