{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T12:13:53Z","timestamp":1775132033818,"version":"3.50.1"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s00530-025-02168-8","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T07:31:42Z","timestamp":1770103902000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual-path consistency constrained concept erasure for text-to-image diffusion models"],"prefix":"10.1007","volume":"32","author":[{"given":"Xiaoran","family":"Bai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuangyan","family":"Yue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,3]]},"reference":[{"key":"2168_CR1","doi-asserted-by":"crossref","unstructured":"Arad, D., Orgad, H., Belinkov, Y.: Refact: updating text-to-image models by editing the text encoder. arXiv:2306.00738 (2023)","DOI":"10.18653\/v1\/2024.naacl-long.140"},{"key":"2168_CR2","doi-asserted-by":"crossref","unstructured":"Bai, T., Luo, J., Zhao, J., et\u00a0al.: Recent advances in adversarial training for adversarial robustness. arXiv:2102.01356 (2021)","DOI":"10.24963\/ijcai.2021\/591"},{"key":"2168_CR3","unstructured":"Bedapudi, P.: Nudenet: neural nets for nudity classification, detection and selective censoring (2019). https:\/\/github.com\/vladmandic\/nudenet"},{"key":"2168_CR4","unstructured":"Chin, Z.Y., Jiang, C.M., Huang, C.C., et\u00a0al.: Prompting4debugging: red-teaming text-to-image diffusion models by finding problematic prompts. arXiv:2309.06135 (2023)"},{"key":"2168_CR5","unstructured":"Devlin, K., Cheetham, J.: Fake trump arrest photos: how to spot an ai-generated image. BBC News 24 (2023)"},{"key":"2168_CR6","doi-asserted-by":"publisher","first-page":"58648","DOI":"10.52202\/075280-2556","volume":"36","author":"C Du","year":"2023","unstructured":"Du, C., Li, Y., Qiu, Z., et al.: Stable diffusion is unstable. Adv. Neural. Inf. Process. Syst. 36, 58648\u201358669 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2168_CR7","unstructured":"Esser, P., Kulal, S., Blattmann, A., et\u00a0al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"2168_CR8","doi-asserted-by":"crossref","unstructured":"Gandikota, R., Materzynska, J., Fiotto-Kaufman, J., et\u00a0al.: Erasing concepts from diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2426\u20132436 (2023)","DOI":"10.1109\/ICCV51070.2023.00230"},{"key":"2168_CR9","doi-asserted-by":"crossref","unstructured":"Gandikota, R., Orgad, H., Belinkov, Y., et\u00a0al.: Unified concept editing in diffusion models. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5111\u20135120 (2024)","DOI":"10.1109\/WACV57701.2024.00503"},{"key":"2168_CR10","doi-asserted-by":"crossref","unstructured":"Gong, C., Chen, K., Wei, Z., et\u00a0al.: Reliable and efficient concept erasure of text-to-image diffusion models. In: European Conference on Computer Vision, Springer, pp. 73\u201388 (2024)","DOI":"10.1007\/978-3-031-73668-1_5"},{"key":"2168_CR11","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"2168_CR12","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv:1412.6572 (2014)"},{"key":"2168_CR13","unstructured":"Guo, D., Rush, A.M., Kim, Y.: Parameter-efficient transfer learning with diff pruning. arXiv:2012.07463 (2020)"},{"key":"2168_CR14","unstructured":"Han, Z., Gao, C., Liu, J., et\u00a0al.: Parameter-efficient fine-tuning for large models: a comprehensive survey. arXiv:2403.14608 (2024)"},{"key":"2168_CR15","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv:2207.12598 (2022)"},{"issue":"2","key":"2168_CR16","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu, E.J., Shen, Y., Wallis, P., et al.: Lora: low-rank adaptation of large language models. ICLR 1(2), 3 (2022)","journal-title":"ICLR"},{"key":"2168_CR17","doi-asserted-by":"crossref","unstructured":"Huang, C.P., Chang, K.P., Tsai, C.T., et\u00a0al.: Receler: reliable concept erasing of text-to-image diffusion models via lightweight erasers. In: European Conference on Computer Vision, Springer, pp. 360\u2013376 (2024)","DOI":"10.1007\/978-3-031-73661-2_20"},{"key":"2168_CR18","unstructured":"Hunter, T.: Ai porn is easy to make now. for women, that\u2019s a nightmare. The Washington Post (2023)"},{"key":"2168_CR19","unstructured":"Kim, C., Qi, Y.: A comprehensive survey on concept erasure in text-to-image diffusion models. arXiv:2502.14896 (2025)"},{"key":"2168_CR20","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes (2013)"},{"key":"2168_CR21","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images. Technical report, Toronto, ON, Canada (2009). https:\/\/www.cs.toronto.edu\/~kriz\/learning-features-2009-TR.pdf"},{"key":"2168_CR22","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., et\u00a0al.: 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":"2168_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., et\u00a0al.: Microsoft coco: common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part v 13, pp. 740\u2013755, Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2168_CR24","first-page":"1950","volume":"35","author":"H Liu","year":"2022","unstructured":"Liu, H., Tam, D., Muqeeth, M., et al.: Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning. Adv. Neural. Inf. Process. Syst. 35, 1950\u20131965 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2168_CR25","doi-asserted-by":"crossref","unstructured":"Liu, H., Wu, Y., Zhai, S., et\u00a0al.: Riatig: reliable and imperceptible adversarial text-to-image generation with natural prompts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20585\u201320594 (2023)","DOI":"10.1109\/CVPR52729.2023.01972"},{"key":"2168_CR26","doi-asserted-by":"crossref","unstructured":"Liu, S., Zeng, Z., Ren, T., et\u00a0al.: Grounding dino: marrying dino with grounded pre-training for open-set object detection. In: European Conference on Computer Vision, Springer, pp. 38\u201355 (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"2168_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Y., An, J., Zhang, W., et\u00a0al.: Disrupting diffusion: token-level attention erasure attack against diffusion-based customization. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 3587\u20133596 (2024)","DOI":"10.1145\/3664647.3681243"},{"key":"2168_CR28","unstructured":"Madry, A., Makelov, A., Schmidt, L., et\u00a0al.: Towards deep learning models resistant to adversarial attacks. arXiv:1706.06083 (2017)"},{"key":"2168_CR29","unstructured":"Marcelo, P.: Fact focus: fake image of pentagon explosion briefly sends jitters through stock market. AP News 23 (2023)"},{"key":"2168_CR30","doi-asserted-by":"crossref","unstructured":"Ni M, Wu C, Wang X, et\u00a0al (2024) Ores: Open-vocabulary responsible visual synthesis. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 21473\u201321481","DOI":"10.1609\/aaai.v38i19.30144"},{"key":"2168_CR31","doi-asserted-by":"crossref","unstructured":"Ni, Z., Wei, L., Li, J., et\u00a0al.: Degeneration-tuning: using scrambled grid shield unwanted concepts from stable diffusion. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 8900\u20138909 (2023)","DOI":"10.1145\/3581783.3611867"},{"key":"2168_CR32","doi-asserted-by":"crossref","unstructured":"Orgad, H., Kawar, B., Belinkov, Y.: Editing implicit assumptions in text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7053\u20137061 (2023)","DOI":"10.1109\/ICCV51070.2023.00649"},{"key":"2168_CR33","doi-asserted-by":"crossref","unstructured":"Pfeiffer, J., Kamath, A., R\u00fcckl\u00e9, A., et\u00a0al.: Adapterfusion: non-destructive task composition for transfer learning. arXiv:2005.00247 (2020)","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"2168_CR34","doi-asserted-by":"crossref","unstructured":"Poppi, S., Poppi, T., Cocchi, F., et\u00a0al.: Safe-clip: removing nsfw concepts from vision-and-language models. In: European Conference on Computer Vision, Springer, pp. 340\u2013356 (2024)","DOI":"10.1007\/978-3-031-73668-1_20"},{"key":"2168_CR35","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, PmLR, pp. 8748\u20138763 (2021)"},{"key":"2168_CR36","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., et\u00a0al.: Hierarchical text-conditional image generation with clip latents. arXiv:2204.06125 1(2):3 (2022)"},{"key":"2168_CR37","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., et\u00a0al.: 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":"2168_CR38","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., et\u00a0al.: 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":"2168_CR39","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: Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, pp. 1350\u20131361 (2022)","DOI":"10.1145\/3531146.3533192"},{"key":"2168_CR40","doi-asserted-by":"crossref","unstructured":"Schramowski, P., Brack, M., Deiseroth, B., et\u00a0al.: Safe latent diffusion: mitigating inappropriate degeneration in diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22522\u201322531 (2023)","DOI":"10.1109\/CVPR52729.2023.02157"},{"key":"2168_CR41","doi-asserted-by":"crossref","unstructured":"Schramowski, P., Brack, M., Deiseroth, B., et\u00a0al.: Safe latent diffusion: mitigating inappropriate degeneration in diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22522\u201322531 (2023)","DOI":"10.1109\/CVPR52729.2023.02157"},{"key":"2168_CR42","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., et al.: Laion-5b: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2168_CR43","unstructured":"Sinitsin, A., Plokhotnyuk, V., Pyrkin, D., et\u00a0al.: Editable neural networks. arXiv:2004.00345 (2020)"},{"key":"2168_CR44","doi-asserted-by":"crossref","unstructured":"Somepalli, G., Singla, V., Goldblum, M., et\u00a0al.: Diffusion art or digital forgery? investigating data replication in diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6048\u20136058 (2023)","DOI":"10.1109\/CVPR52729.2023.00586"},{"key":"2168_CR45","unstructured":"Tsai, Y.L., Hsu, C.Y., Xie, C., et\u00a0al.: Ring-a-bell! how reliable are concept removal methods for diffusion models? arXiv:2310.10012 (2023)"},{"key":"2168_CR46","unstructured":"Wang, H., Spinelli, M., Wang, Q., et\u00a0al.: Instantstyle: free lunch towards style-preserving in text-to-image generation. arXiv:2404.02733 (2024)"},{"key":"2168_CR47","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wei, Y., Li, F., et\u00a0al.: Ace: anti-editing concept erasure in text-to-image models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 23505\u201323515 (2025)","DOI":"10.1109\/CVPR52734.2025.02189"},{"key":"2168_CR48","doi-asserted-by":"crossref","unstructured":"Wang, Z.J., Montoya, E., Munechika, D., et\u00a0al.: Diffusiondb: a large-scale prompt gallery dataset for text-to-image generative models. arXiv:2210.14896 (2022)","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"2168_CR49","doi-asserted-by":"crossref","unstructured":"Yang, Y., Gao, R., Wang, X., et\u00a0al.: Mma-diffusion: multimodal attack on diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7737\u20137746 (2024)","DOI":"10.1109\/CVPR52733.2024.00739"},{"key":"2168_CR50","first-page":"76380","volume":"37","author":"Y Yang","year":"2024","unstructured":"Yang, Y., Gao, R., Yang, X., et al.: Guardt2i: Defending text-to-image models from adversarial prompts. Adv. Neural. Inf. Process. Syst. 37, 76380\u201376403 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2168_CR51","unstructured":"Zaken, E.B., Ravfogel, S., Goldberg, Y.: Bitfit: simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv:2106.10199 (2021)"},{"key":"2168_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, G., Wang, K., Xu, X., et\u00a0al.: Forget-me-not: learning to forget in text-to-image diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1755\u20131764 (2024)","DOI":"10.1109\/CVPRW63382.2024.00182"},{"key":"2168_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"2168_CR54","first-page":"11127","volume":"36","author":"S Zhao","year":"2023","unstructured":"Zhao, S., Chen, D., Chen, Y.C., et al.: Uni-controlnet: all-in-one control to text-to-image diffusion models. Adv. Neural. Inf. Process. Syst. 36, 11127\u201311150 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02168-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-02168-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02168-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T11:36:36Z","timestamp":1775129796000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-02168-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,3]]},"references-count":54,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["2168"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-02168-8","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,3]]},"assertion":[{"value":"18 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"127"}}