{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:09:14Z","timestamp":1765339754490,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755326","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:15Z","timestamp":1761375255000},"page":"11462-11471","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["NDM: A Noise-driven Detection and Mitigation Framework against Implicit Sexual Intentions in Text-to-Image Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5294-2093","authenticated-orcid":false,"given":"Yitong","family":"Sun","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7978-2372","authenticated-orcid":false,"given":"Yao","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2514-6551","authenticated-orcid":false,"given":"Ruochen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0847-9485","authenticated-orcid":false,"given":"Huanran","family":"Chen","sequence":"additional","affiliation":[{"name":"College of AI, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0481-5855","authenticated-orcid":false,"given":"Shouwei","family":"Ruan","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2261-4268","authenticated-orcid":false,"given":"Ranjie","family":"Duan","sequence":"additional","affiliation":[{"name":"Security Group, Alibaba Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0778-8377","authenticated-orcid":false,"given":"Xingxing","family":"Wei","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Principal component analysis","author":"Abdi Herv\u00e9","year":"2010","unstructured":"Herv\u00e9 Abdi and Lynne J Williams. 2010. Principal component analysis. Wiley interdisciplinary reviews: computational statistics, Vol. 2, 4 (2010), 433-459."},{"key":"e_1_3_2_1_2_1","first-page":"78126","article-title":"Diffinfinite: Large mask-image synthesis via parallel random patch diffusion in histopathology","volume":"36","author":"Aversa Marco","year":"2023","unstructured":"Marco Aversa, Gabriel Nobis, Miriam H\u00e4gele, Kai Standvoss, Mihaela Chirica, Roderick Murray-Smith, Ahmed M Alaa, Lukas Ruff, Daniela Ivanova, Wojciech Samek, et al., 2023. Diffinfinite: Large mask-image synthesis via parallel random patch diffusion in histopathology. Advances in Neural Information Processing Systems, Vol. 36 (2023), 78126-78141.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","volume-title":"The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise. arXiv preprint arXiv:2406.01970","author":"Ban Yuanhao","year":"2024","unstructured":"Yuanhao Ban, Ruochen Wang, Tianyi Zhou, Boqing Gong, Cho-Jui Hsieh, and Minhao Cheng. 2024. The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise. arXiv preprint arXiv:2406.01970 (2024)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604722"},{"key":"e_1_3_2_1_5_1","volume-title":"RoentGen: Vision-Language Foundation Model for Chest X-ray Generation. arXiv preprint arXiv:2211.12737","author":"Chambon Pierre","year":"2022","unstructured":"Pierre Chambon, Christian Bluethgen, Curtis P. Langlotz, and Akshay Chaudhari. 2022. RoentGen: Vision-Language Foundation Model for Chest X-ray Generation. arXiv preprint arXiv:2211.12737 (2022)."},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Machine Learning.","author":"Chen Pin-Yu","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 International Conference on Machine Learning."},{"key":"e_1_3_2_1_7_1","unstructured":"The complete list of banned words in midjourney you need to know. 2023. https:\/\/blog.easyprompt.xyz\/the-complete-list-of-banned-words-in-midjourney-you-need-to-know-12111a5bbf87"},{"key":"e_1_3_2_1_8_1","volume-title":"Support-vector networks. Machine learning","author":"Cortes Corinna","year":"1995","unstructured":"Corinna Cortes and Vladimir Vapnik. 1995. Support-vector networks. Machine learning, Vol. 20 (1995), 273-297."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-1809.1936.tb02137.x"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00230"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00503"},{"key":"e_1_3_2_1_12_1","volume-title":"European Conference on Computer Vision. Springer, 73-88","author":"Gong Chao","year":"2024","unstructured":"Chao Gong, Kai Chen, Zhipeng Wei, Jingjing Chen, and Yu-Gang Jiang. 2024. Reliable and efficient concept erasure of text-to-image diffusion models. In European Conference on Computer Vision. Springer, 73-88."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-024-09694-w"},{"key":"e_1_3_2_1_15_1","volume-title":"Ronan Le Bras, and Yejin Choi","author":"Hessel Jack","year":"2021","unstructured":"Jack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, and Yejin Choi. 2021. Clipscore: A reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)."},{"key":"e_1_3_2_1_16_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_17_1","volume-title":"Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)."},{"key":"e_1_3_2_1_18_1","volume-title":"European Conference on Computer Vision. Springer, 360-376","author":"Huang Chi-Pin","year":"2024","unstructured":"Chi-Pin Huang, Kai-Po Chang, Chung-Ting Tsai, Yung-Hsuan Lai, Fu-En Yang, and Yu-Chiang Frank Wang. 2024. Receler: Reliable concept erasing of text-to-image diffusion models via lightweight erasers. In European Conference on Computer Vision. Springer, 360-376."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i25.34821"},{"key":"e_1_3_2_1_20_1","volume-title":"Breaking the ceiling: Exploring the potential of jailbreak attacks through expanding strategy space. arXiv preprint arXiv:2505.21277","author":"Huang Yao","year":"2025","unstructured":"Yao Huang, Yitong Sun, Shouwei Ruan, Yichi Zhang, Yinpeng Dong, and Xingxing Wei. 2025b. Breaking the ceiling: Exploring the potential of jailbreak attacks through expanding strategy space. arXiv preprint arXiv:2505.21277 (2025)."},{"key":"e_1_3_2_1_21_1","first-page":"740","volume-title":"Switzerland","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer vision-ECCV 2014: 13th European conference, zurich, Switzerland, September 6-12, 2014, proceedings, part v 13. Springer, 740-755."},{"key":"e_1_3_2_1_22_1","volume-title":"Safetydpo: Scalable safety alignment for text-to-image generation. arXiv preprint arXiv:2412.10493","author":"Liu Runtao","year":"2024","unstructured":"Runtao Liu, Chen I Chieh, Jindong Gu, Jipeng Zhang, Renjie Pi, Qifeng Chen, Philip Torr, Ashkan Khakzar, and Fabio Pizzati. 2024a. Safetydpo: Scalable safety alignment for text-to-image generation. arXiv preprint arXiv:2412.10493 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"European Conference on Computer Vision. Springer, 93-109","author":"Liu Runtao","year":"2024","unstructured":"Runtao Liu, Ashkan Khakzar, Jindong Gu, Qifeng Chen, Philip Torr, and Fabio Pizzati. 2024b. Latent guard: a safety framework for text-to-image generation. In European Conference on Computer Vision. Springer, 93-109."},{"key":"e_1_3_2_1_24_1","unstructured":"Machine Vision & Learning Group LMU. 2022. Safety Checker Model Card. https:\/\/huggingface.co\/CompVis\/stable-diffusion-safety-checker. Accessed 29\/09\/2022."},{"key":"e_1_3_2_1_25_1","unstructured":"Midjourney. 2022. https:\/\/www.midjourney.com"},{"key":"e_1_3_2_1_26_1","volume-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741","author":"Nichol Alex","year":"2021","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)."},{"key":"e_1_3_2_1_27_1","volume-title":"Nudenet: Neural nets for nudity classification, detection and selective censoring.","author":"AI","year":"2019","unstructured":"notAI tech. 2019. Nudenet: Neural nets for nudity classification, detection and selective censoring. (2019)."},{"key":"e_1_3_2_1_28_1","first-page":"285","article-title":"A threshold selection method from gray-level histograms","volume":"11","author":"Nobuyuki Otsu","year":"1975","unstructured":"Nobuyuki Otsu et al., 1975. A threshold selection method from gray-level histograms. Automatica, Vol. 11, 285-296 (1975), 23-27.","journal-title":"Automatica"},{"key":"e_1_3_2_1_29_1","volume-title":"European Conference on Computer Vision. Springer, 340-356","author":"Poppi Samuele","year":"2024","unstructured":"Samuele Poppi, Tobia Poppi, Federico Cocchi, Marcella Cornia, Lorenzo Baraldi, and Rita Cucchiara. 2024. Safe-CLIP: Removing NSFW concepts from vision-and-language models. In European Conference on Computer Vision. Springer, 340-356."},{"key":"e_1_3_2_1_30_1","volume-title":"Not all noises are created equally: Diffusion noise selection and optimization. arXiv preprint arXiv:2407.14041","author":"Qi Zipeng","year":"2024","unstructured":"Zipeng Qi, Lichen Bai, Haoyi Xiong, and Zeke Xie. 2024. Not all noises are created equally: Diffusion noise selection and optimization. arXiv preprint arXiv:2407.14041 (2024)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3616679"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_33_1","volume-title":"Towards NSFW-Free Text-to-Image Generation via Safety-Constraint Direct Preference Optimization. arXiv preprint arXiv:2504.14290","author":"Ruan Shouwei","year":"2025","unstructured":"Shouwei Ruan, Zhenyu Wu, Yao Huang, Ruochen Zhang, Yitong Sun, Caixin Kang, and Xingxing Wei. 2025. Towards NSFW-Free Text-to-Image Generation via Safety-Constraint Direct Preference Optimization. arXiv preprint arXiv:2504.14290 (2025)."},{"key":"e_1_3_2_1_34_1","volume-title":"Burcu Karagol Ayan, Tim Salimans, et al.","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al., 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing systems, Vol. 35 (2022), 36479-36494."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02157"},{"key":"e_1_3_2_1_36_1","unstructured":"Christoph Schuhmann Romain Beaumont Richard Vencu Cade Gordon Ross Wightman Mehdi Cherti Theo Coombes Aarush Katta Clayton Mullis Mitchell Wortsman et al. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in neural information processing systems Vol. 35 (2022) 25278-25294."},{"key":"e_1_3_2_1_37_1","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 ICLR."},{"key":"e_1_3_2_1_38_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_39_1","volume-title":"Diffusion-based visual art creation: A survey and new perspectives. Comput. Surveys","author":"Wang Bingyuan","year":"2024","unstructured":"Bingyuan Wang, Qifeng Chen, and Zeyu Wang. 2024. Diffusion-based visual art creation: A survey and new perspectives. Comput. Surveys (2024)."},{"key":"e_1_3_2_1_40_1","volume-title":"Mmdt: Decoding the trustworthiness and safety of multimodal foundation models. arXiv preprint arXiv:2503.14827","author":"Xu Chejian","year":"2025","unstructured":"Chejian Xu, Jiawei Zhang, Zhaorun Chen, Chulin Xie, Mintong Kang, Yujin Potter, Zhun Wang, Zhuowen Yuan, Alexander Xiong, Zidi Xiong, et al., 2025b. Mmdt: Decoding the trustworthiness and safety of multimodal foundation models. arXiv preprint arXiv:2503.14827 (2025)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00299"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00739"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00123"},{"key":"e_1_3_2_1_44_1","volume-title":"Safree: Training-free and adaptive guard for safe text-to-image and video generation. arXiv preprint arXiv:2410.12761","author":"Yoon Jaehong","year":"2024","unstructured":"Jaehong Yoon, Shoubin Yu, Vaidehi Patil, Huaxiu Yao, and Mohit Bansal. 2024. Safree: Training-free and adaptive guard for safe text-to-image and video generation. arXiv preprint arXiv:2410.12761 (2024)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.773"},{"key":"e_1_3_2_1_46_1","volume-title":"Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675","author":"Zhang Tianyi","year":"2019","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2019. Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675 (2019)."},{"key":"e_1_3_2_1_47_1","first-page":"49279","article-title":"Multitrust: A comprehensive benchmark towards trustworthy multimodal large language models","volume":"37","author":"Zhang Yichi","year":"2024","unstructured":"Yichi Zhang, Yao Huang, Yitong Sun, Chang Liu, Zhe Zhao, Zhengwei Fang, Yifan Wang, Huanran Chen, Xiao Yang, Xingxing Wei, et al., 2024a. Multitrust: A comprehensive benchmark towards trustworthy multimodal large language models. Advances in Neural Information Processing Systems, Vol. 37 (2024), 49279-49383.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_48_1","volume-title":"European Conference on Computer Vision. Springer, 385-403","author":"Zhang Yimeng","year":"2024","unstructured":"Yimeng Zhang, Jinghan Jia, Xin Chen, Aochuan Chen, Yihua Zhang, Jiancheng Liu, Ke Ding, and Sijia Liu. 2024b. To generate or not? safety-driven unlearned diffusion models are still easy to generate unsafe images... for now. In European Conference on Computer Vision. Springer, 385-403."},{"key":"e_1_3_2_1_49_1","volume-title":"Realsafe-r1: Safety-aligned deepseek-r1 without compromising reasoning capability. arXiv preprint arXiv:2504.10081","author":"Zhang Yichi","year":"2025","unstructured":"Yichi Zhang, Zihao Zeng, Dongbai Li, Yao Huang, Zhijie Deng, and Yinpeng Dong. 2025a. Realsafe-r1: Safety-aligned deepseek-r1 without compromising reasoning capability. arXiv preprint arXiv:2504.10081 (2025)."},{"key":"e_1_3_2_1_50_1","volume-title":"Stair: Improving safety alignment with introspective reasoning. arXiv preprint arXiv:2502.02384","author":"Zhang Yichi","year":"2025","unstructured":"Yichi Zhang, Siyuan Zhang, Yao Huang, Zeyu Xia, Zhengwei Fang, Xiao Yang, Ranjie Duan, Dong Yan, Yinpeng Dong, and Jun Zhu. 2025b. Stair: Improving safety alignment with introspective reasoning. arXiv preprint arXiv:2502.02384 (2025)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:04:33Z","timestamp":1765339473000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755326"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":50,"alternative-id":["10.1145\/3746027.3755326","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755326","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}