{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:43:04Z","timestamp":1777657384460,"version":"3.51.4"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730092","type":"print"},{"value":"9783031730108","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"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\/978-3-031-73010-8_27","type":"book-chapter","created":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T13:10:52Z","timestamp":1731157852000},"page":"461-478","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["R.A.C.E. : Robust Adversarial Concept Erasure for\u00a0Secure Text-to-Image Diffusion Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5850-6483","authenticated-orcid":false,"given":"Changhoon","family":"Kim","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3978-918X","authenticated-orcid":false,"given":"Kyle","family":"Min","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0126-8976","authenticated-orcid":false,"given":"Yezhou","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,10]]},"reference":[{"key":"27_CR1","unstructured":"Bedapudi, P.: Nudenet: neural nets for nudity classification, detection and selective censoring, December 2019"},{"key":"27_CR2","unstructured":"Carlini, N., et al.: Extracting training data from diffusion models. ArXiv abs\/2301.13188 (2023). https:\/\/api.semanticscholar.org\/CorpusID:256389993"},{"key":"27_CR3","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. arXiv preprint arXiv:2309.06135 (2023)"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"27_CR5","unstructured":"Devlin, K., Cheetham, J.: Fake trump arrest photos: how to spot an AI-generated image. BBC News (March 2023). https:\/\/www.bbc.com\/news\/technology-68981525"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Fernandez, P., Couairon, G., J\u00e9gou, H., Douze, M., Furon, T.: The stable signature: rooting watermarks in latent diffusion models. arXiv preprint arXiv:2303.15435 (2023)","DOI":"10.1109\/ICCV51070.2023.02053"},{"key":"27_CR8","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. ArXiv abs\/2208.01618 (2022). https:\/\/api.semanticscholar.org\/CorpusID:251253049"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Gandikota, R., Materzynska, J., Fiotto-Kaufman, J., Bau, D.: Erasing concepts from diffusion models. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2426\u20132436 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257495777","DOI":"10.1109\/ICCV51070.2023.00230"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"27_CR11","unstructured":"Heng, A., Soh, H.: Selective amnesia: a continual learning approach to forgetting in deep generative models. ArXiv abs\/2305.10120 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258740988"},{"key":"27_CR12","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. arXiv preprint arXiv:2104.08718 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"27_CR13","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. In: Advances in Neural Information Processing Systems, pp. 6626\u20136637 (2017)"},{"key":"27_CR14","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"27_CR15","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Howard, J., Gugger, S.: Fastai: a layered api for deep learning. Inf. 11, 108 (2020). https:\/\/api.semanticscholar.org\/CorpusID:211082837","DOI":"10.3390\/info11020108"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Kim, C., Min, K., Patel, M., Cheng, S., Yang, Y.: Wouaf: weight modulation for user attribution and fingerprinting in text-to-image diffusion models. arXiv preprint arXiv:2306.04744 (2023)","DOI":"10.1109\/CVPR52733.2024.00857"},{"key":"27_CR19","unstructured":"Kim, C., Ren, Y., Yang, Y.: Decentralized attribution of generative models. In: International Conference on Learning Representations (2021)"},{"key":"27_CR20","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2014). http:\/\/arxiv.org\/abs\/1412.6980, cite arxiv:1412.6980Comment: Published as a conference paper at the 3rd International Conference for Learning Representations, San Diego, 2015"},{"key":"27_CR21","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: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 22634\u201322645 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257687839","DOI":"10.1109\/ICCV51070.2023.02074"},{"key":"27_CR22","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: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1931\u20131941 (2022). https:\/\/api.semanticscholar.org\/CorpusID:254408780","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Li, A.C., Prabhudesai, M., Duggal, S., Brown, E., Pathak, D.: Your diffusion model is secretly a zero-shot classifier. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2206\u20132217 (October 2023)","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"27_CR24","unstructured":"Li, S., et al.: Get what you want, not what you don\u2019t: image content suppression for text-to-image diffusion models. ArXiv abs\/2402.05375 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267547985"},{"key":"27_CR25","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. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"27_CR26","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)"},{"key":"27_CR27","unstructured":"Marcelo, P.: Fact focus: fake image of pentagon explosion briefly sends jitters through stock market. Associated Press (May 2023). https:\/\/apnews.com\/article\/pentagon-explosion-fake-image-stock-market-jitters-78d5913603bdf9f17cc7a8c77a72e59b"},{"key":"27_CR28","unstructured":"Ni, M., et al.: Ores: open-vocabulary responsible visual synthesis. ArXiv abs\/2308.13785 (2023). https:\/\/api.semanticscholar.org\/CorpusID:261243073"},{"key":"27_CR29","unstructured":"Nichol, A.Q., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. In: International Conference on Machine Learning, pp. 16784\u201316804. PMLR (2022)"},{"key":"27_CR30","unstructured":"Nie, G., Kim, C., Yang, Y., Ren, Y.: Attributing image generative models using latent fingerprints. arXiv preprint arXiv:2304.09752 (2023)"},{"key":"27_CR31","unstructured":"OpenAI: Chatgpt. Online (2022). https:\/\/chat.openai.com\/chat. Accessed 24 Feb 2024"},{"key":"27_CR32","unstructured":"Patel, M., Jung, S., Baral, C., Yang, Y.: $$\\lambda $$-eclipse: multi-concept personalized text-to-image diffusion models by leveraging clip latent space. ArXiv abs\/2402.05195 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267547418"},{"key":"27_CR33","unstructured":"Patel, M., Kim, C.S., Cheng, S., Baral, C., Yang, Y.: Eclipse: a resource-efficient text-to-image prior for image generations. ArXiv abs\/2312.04655 (2023). https:\/\/api.semanticscholar.org\/CorpusID:266149498"},{"key":"27_CR34","unstructured":"Pham, M., Marshall, K.O., Cohen, N., Mittal, G., Hegde, C.: Circumventing concept erasure methods for text-to-image generative models. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=ag3o2T51Ht"},{"key":"27_CR35","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":"27_CR36","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":"27_CR37","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":"27_CR38","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 (CVPR), pp. 10684\u201310695, June 2022","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"27_CR39","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":"27_CR40","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: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22500\u201322510 (2022). https:\/\/api.semanticscholar.org\/CorpusID:251800180","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"27_CR41","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":"27_CR42","unstructured":"Saleh, B., Elgammal, A.: Large-scale classification of fine-art paintings: learning the right metric on the right feature. ArXiv abs\/1505.00855 (2015). https:\/\/api.semanticscholar.org\/CorpusID:14168099"},{"key":"27_CR43","doi-asserted-by":"crossref","unstructured":"Schramowski, P., Brack, M., Deiseroth, B., Kersting, K.: Safe latent diffusion: mitigating inappropriate degeneration in diffusion models. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22522\u201322531 (2022). https:\/\/api.semanticscholar.org\/CorpusID:253420366","DOI":"10.1109\/CVPR52729.2023.02157"},{"key":"27_CR44","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":"27_CR45","doi-asserted-by":"crossref","unstructured":"Somepalli, G., Singla, V., Goldblum, M., Geiping, J., Goldstein, T.: Diffusion art or digital forgery? Investigating data replication in diffusion models. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6048\u20136058 (2022). https:\/\/api.semanticscholar.org\/CorpusID:254366634","DOI":"10.1109\/CVPR52729.2023.00586"},{"key":"27_CR46","unstructured":"Somepalli, G., Singla, V., Goldblum, M., Geiping, J., Goldstein, T.: Understanding and mitigating copying in diffusion models. ArXiv abs\/2305.20086 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258987384"},{"key":"27_CR47","unstructured":"Tsai, Y.L., et al.: Ring-a-bell! How reliable are concept removal methods for diffusion models? ArXiv abs\/2310.10012 (2023). https:\/\/api.semanticscholar.org\/CorpusID:264146485"},{"key":"27_CR48","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhang, Y., Ji, Z., Bai, J., Zhang, L., Zuo, W.: Elite: encoding visual concepts into textual embeddings for customized text-to-image generation. 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 15897\u201315907 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257219968","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"27_CR49","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. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"27_CR50","unstructured":"Wen, Y., Kirchenbauer, J., Geiping, J., Goldstein, T.: Tree-ring watermarks: fingerprints for diffusion images that are invisible and robust. arXiv preprint arXiv:2305.20030 (2023)"},{"key":"27_CR51","unstructured":"Wu, B., et al.: Visual transformers: token-based image representation and processing for computer vision. ArXiv abs\/2006.03677 (2020). https:\/\/api.semanticscholar.org\/CorpusID:219531480"},{"key":"27_CR52","unstructured":"Wu, Y., Zhang, J., Kerschbaum, F., Zhang, T.: Backdooring textual inversion for concept censorship. ArXiv abs\/2308.10718 (2023). https:\/\/api.semanticscholar.org\/CorpusID:261049298"},{"key":"27_CR53","unstructured":"Yang, Y., Gao, R., Wang, X., Xu, N., Xu, Q.: Mma-diffusion: multimodal attack on diffusion models. ArXiv abs\/2311.17516 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265498727"},{"key":"27_CR54","doi-asserted-by":"crossref","unstructured":"Yu, N., Skripniuk, V., Abdelnabi, S., Fritz, M.: Artificial fingerprinting for generative models: rooting deepfake attribution in training data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14448\u201314457 (2021)","DOI":"10.1109\/ICCV48922.2021.01418"},{"key":"27_CR55","unstructured":"Yu, N., Skripniuk, V., Chen, D., Davis, L., Fritz, M.: Responsible disclosure of generative models using scalable fingerprinting. arXiv preprint arXiv:2012.08726 (2020)"},{"key":"27_CR56","unstructured":"Zhang, E., Wang, K., Xu, X., Wang, Z., Shi, H.: Forget-me-not: learning to forget in text-to-image diffusion models. ArXiv abs\/2303.17591 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257833863"},{"key":"27_CR57","unstructured":"Zhang, K.A., Xu, L., Cuesta-Infante, A., Veeramachaneni, K.: Robust invisible video watermarking with attention (2019)"},{"key":"27_CR58","unstructured":"Zhang, Y., et al.: To generate or not? Safety-driven unlearned diffusion models are still easy to generate unsafe images ... for now. ArXiv abs\/2310.11868 (2023). https:\/\/api.semanticscholar.org\/CorpusID:264289091"},{"key":"27_CR59","unstructured":"Zheng, Y., Yeh, R.A.: Imma: immunizing text-to-image models against malicious adaptation. ArXiv abs\/2311.18815 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265506125"}],"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\/978-3-031-73010-8_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T14:08:02Z","timestamp":1731161282000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73010-8_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,10]]},"ISBN":["9783031730092","9783031730108"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73010-8_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,10]]},"assertion":[{"value":"10 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"}}]}}